© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15003
    Prev
    Next
    INDEX
    Explanations

    code and database snippets

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     GK
    -1.23
     LK
    -1.17
     JK
    -1.16
     MK
    -1.13
     PK
    -1.12
     TK
    -1.10
     FK
    -1.09
    MK
    -1.09
     RK
    -1.09
     DK
    -1.08
    POSITIVE LOGITS
    onActivityResult
    0.40
    intahan
    0.35
    SPATH
    0.33
     lámina
    0.33
    CSM
    0.32
    errHandler
    0.31
    院
    0.31
    潮
    0.31
    æv
    0.31
    ValueStyle
    0.31
    Activations Density 0.455%

    No Known Activations