© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8324
    Prev
    Next
    INDEX
    Explanations

    pronouns, auxiliary verbs and words denoting provenance, and also the word "word"

    oai_token-act-pair · gemini-2.0-flash

    truth-telling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     المعيارى
    -0.91
    contentLoaded
    -0.87
     resourceCulture
    -0.83
    Cyfeiriadau
    -0.79
    +#+#
    -0.79
    antMatchers
    -0.77
     ExecuteAsync
    -0.76
    mbg
    -0.75
     ModelExpression
    -0.72
     GenerationType
    -0.70
    POSITIVE LOGITS
     word
    1.47
    word
    1.29
     palabra
    1.11
    Word
    1.10
     Word
    1.09
    WORD
    1.07
     WORD
    1.04
     palavra
    0.87
     words
    0.85
    words
    0.85
    Activations Density 1.255%

    No Known Activations