© 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. 9129
    Prev
    Next
    INDEX
    Explanations

    code syntax related to function definitions, calls, and interfaces

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
     myſelf
    -0.82
    tvguidetime
    -0.80
    المناصب
    -0.80
    PerformLayout
    -0.79
     intptr
    -0.73
     poffible
    -0.73
     onOptions
    -0.71
    IntoConstraints
    -0.70
     snippetHide
    -0.70
     Jefus
    -0.70
    POSITIVE LOGITS
    <bos>
    0.53
    ogra
    0.45
     Down
    0.44
     pri
    0.43
     Pri
    0.42
     di
    0.41
     qu
    0.40
     "
    0.40
     down
    0.40
     au
    0.40
    Activations Density 1.465%

    No Known Activations