© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16237
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that research has recently been done or findings that have been shown

    oai_token-act-pair · gemini-2.0-flash

    been

    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
    GRANTED
    -0.59
     كومونز
    -0.57
    lapsingToolbar
    -0.55
    bolista
    -0.52
    ronpa
    -0.51
     Gra
    -0.51
    rawDesc
    -0.50
    drawable
    -0.50
    󠁢
    -0.49
     managed
    -0.49
    POSITIVE LOGITS
     autorytatywna
    0.65
    "';
    0.57
    ConstraintMaker
    0.56
    rsiniz
    0.56
     Wikimedijinoj
    0.56
     nahilalakip
    0.54
    */),
    0.53
    }}</
    0.52
     estekak
    0.52
    KommentareTeilen
    0.52
    Activations Density 3.414%

    No Known Activations