© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8482
    Prev
    Next
    INDEX
    Explanations

    language used in business to persuade customers

    oai_token-act-pair · gemini-2.0-flash

    business

    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
    ViewFeatures
    -0.68
     مرئيه
    -0.62
    UnusedPrivate
    -0.60
    ContextHolder
    -0.57
    хьтан
    -0.57
     дописавши
    -0.55
    TypedDataSet
    -0.54
    Personensuche
    -0.53
     Drapeau
    -0.53
     Wellen
    -0.51
    POSITIVE LOGITS
    quelize
    0.51
     saites
    0.47
    writeFieldEnd
    0.44
    digm
    0.43
    ellees
    0.42
     guste
    0.41
    ьере
    0.41
    プローチ
    0.40
    Subviews
    0.40
    ASCII
    0.40
    Activations Density 0.187%

    No Known Activations