© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11871
    Prev
    Next
    INDEX
    Explanations

    variations of the word "Decide".

    oai_token-act-pair · gemini-2.0-flash

    Dec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Dec
    -0.57
    Dec
    -0.56
    TagHelper
    -0.53
    dec
    -0.51
    ViewFeatures
    -0.46
     dec
    -0.45
     DEC
    -0.45
     de
    -0.44
     deca
    -0.44
     Deo
    -0.44
    POSITIVE LOGITS
    клопе
    0.73
     Roskov
    0.68
    DockStyle
    0.63
     Monfieur
    0.61
     חיצוניים
    0.58
     Perſ
    0.58
    ForValue
    0.57
     שוליים
    0.56
     vela
    0.55
     réfrig
    0.52
    Activations Density 1.988%

    No Known Activations