© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9578
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to searching for a particular thing

    oai_token-act-pair · gemini-2.0-flash

    Find/For

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ویکی‌پدیای
    -0.69
    #+#
    -0.66
    bewerken
    -0.63
     незавершена
    -0.60
     nahilalakip
    -0.58
     ProtoMessage
    -0.57
    FunctionFlags
    -0.57
     disambiguazione
    -0.55
    featureID
    -0.55
     سكانية
    -0.54
    POSITIVE LOGITS
     someone
    0.56
     meaningful
    0.52
     supports
    0.50
     accurate
    0.50
     permission
    0.49
     consistent
    0.49
    Relevant
    0.48
     insights
    0.47
     support
    0.46
     doğru
    0.46
    Activations Density 6.810%

    No Known Activations