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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11803
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to interest, science and opportunities to obtain more information

    oai_token-act-pair · gemini-2.0-flash

    tea

    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
    ISupport
    -0.71
    twimg
    -0.57
    QMetaType
    -0.51
    ########.
    -0.50
    Géographie
    -0.49
    וויק
    -0.48
    transQ
    -0.48
    verlauf
    -0.48
    Източници
    -0.47
    principalTable
    -0.46
    POSITIVE LOGITS
     favourably
    0.58
    rouvez
    0.58
    CodedInputStream
    0.54
    ędziesz
    0.54
    TextInputLayout
    0.52
     "..\..\..\
    0.52
     oid
    0.51
     spiro
    0.51
     honourable
    0.51
     publick
    0.51
    Activations Density 0.530%

    No Known Activations