© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15149
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to identify various aspects of speech or writing, including quotes, emphasis, references (like versions, editions, or settings), the end of a phrase, and sometimes a general level of formality.

    oai_token-act-pair · gemini-2.0-flash

    media and technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.77
    principalTable
    -0.65
     DataTypes
    -0.55
    IRUS
    -0.53
    enderror
    -0.53
    iläum
    -0.52
     "..\..\..\
    -0.52
     bezeichneter
    -0.51
     للاسماء
    -0.50
    MessageOf
    -0.50
    POSITIVE LOGITS
    WebVitals
    0.61
    stdc
    0.52
     Jérusalem
    0.51
    providedIn
    0.51
     ejus
    0.49
    getch
    0.49
    Hyderabad
    0.48
    basicConfig
    0.48
    Chennai
    0.48
    derabad
    0.47
    Activations Density 0.982%

    No Known Activations