© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10805
    Prev
    Next
    INDEX
    Explanations

    sentences that have some kind of qualification or legal and biological jargon

    oai_token-act-pair · gemini-2.0-flash

    respects

    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
     createState
    -0.73
     endwhile
    -0.69
    SharedCtor
    -0.69
     يتيمه
    -0.68
    Vorlage
    -0.66
    WebElementEntity
    -0.65
    StoryboardSegue
    -0.65
     Domes
    -0.64
    SequentialGroup
    -0.63
     ExecuteAsync
    -0.63
    POSITIVE LOGITS
    İstinadlar
    0.51
     special
    0.46
     situation
    0.43
     Situation
    0.41
    šić
    0.40
     McAllister
    0.40
     nytt
    0.40
     Special
    0.39
     Imp
    0.39
     live
    0.38
    Activations Density 1.790%

    No Known Activations