© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15277
    Prev
    Next
    INDEX
    Explanations

    book titles and related words from reviews and discussions

    oai_token-act-pair · gemini-2.0-flash

    book reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    addCriterion
    -0.62
     liever
    -0.58
    <bos>
    -0.52
     ooit
    -0.50
     transfieras
    -0.49
     Bioaccumulative
    -0.48
    Portail
    -0.48
    AsUp
    -0.47
     سكانية
    -0.47
     ſhould
    -0.46
    POSITIVE LOGITS
    upassen
    0.86
    RegistryLite
    0.66
    leau
    0.60
     Familienname
    0.59
     ddelweddau
    0.56
    racite
    0.56
    ackerel
    0.55
    Exercises
    0.55
     GENERATED
    0.55
    heira
    0.55
    Activations Density 0.544%

    No Known Activations