© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15080
    Prev
    Next
    INDEX
    Explanations

    LaTeX and other code snippets interspersed in text.

    oai_token-act-pair · gemini-2.0-flash

    math symbols/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    AutoScaleMode
    -0.52
    ClientSize
    -0.47
     multiple
    -0.44
    laka
    -0.44
     �
    -0.43
    ennie
    -0.43
     Levin
    -0.43
    ändigt
    -0.43
    ENTA
    -0.43
     $=
    -0.43
    POSITIVE LOGITS
    <bos>
    1.66
     المعيارى
    0.88
    __':
    0.84
     متعلقه
    0.75
    uxxxx
    0.73
     ModelExpression
    0.71
    __":
    0.69
    __':
    0.69
    .*")]
    0.68
     Theſe
    0.67
    Activations Density 0.808%

    No Known Activations