© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6968
    Prev
    Next
    INDEX
    Explanations

    phrases related to possibility or guessing

    oai_token-act-pair · gemini-2.0-flash

    statements of possibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    neum
    -0.55
    IMI
    -0.52
    Portail
    -0.52
     Situ
    -0.49
     ví
    -0.49
    BitmapFactory
    -0.48
     Venue
    -0.48
     ongles
    -0.48
     Nó
    -0.48
     Kraj
    -0.48
    POSITIVE LOGITS
    aarrggbb
    0.82
    ConstraintMaker
    0.69
     שוליים
    0.66
    évaluateur
    0.64
    matchCondition
    0.62
    ništvo
    0.60
    WithIOException
    0.59
    клопе
    0.59
    šina
    0.59
    DockStyle
    0.58
    Activations Density 1.344%

    No Known Activations