© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14011
    Prev
    Next
    INDEX
    Explanations

    sentences where someone is asking for guidance after making a mistake

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     صوتيه
    -1.27
    RenderAtEndOf
    -1.23
     Efq
    -1.17
    ValueStyle
    -1.15
     Majefty
    -1.14
     ModelExpression
    -1.11
     يتيمه
    -1.11
    expandindo
    -1.10
     متعلقه
    -1.09
    ſelf
    -1.09
    POSITIVE LOGITS
     d
    0.35
     p
    0.31
     ch
    0.31
     b
    0.31
     v
    0.30
    深圳
    0.29
     au
    0.29
     du
    0.29
     g
    0.28
     D
    0.28
    Activations Density 0.544%

    No Known Activations