© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    lines of dialogue

    oai_token-act-pair · gemini-2.0-flash

    commands

    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
    wsgi
    -0.52
     Chwiliwch
    -0.51
    DispatchToProps
    -0.47
     Waray
    -0.47
    Aktualisiert
    -0.46
    colgroup
    -0.46
    ributos
    -0.45
     Cricket
    -0.45
    ();)
    -0.45
     Roskov
    -0.45
    POSITIVE LOGITS
    setViewportView
    0.64
     beginnetje
    0.63
    SharedDtor
    0.60
     cantons
    0.57
     autorytatywna
    0.56
    ValueStyle
    0.56
    +#+#
    0.54
    WebControls
    0.53
     متعلقه
    0.52
    Brainz
    0.51
    Activations Density 0.354%

    No Known Activations