© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12157
    Prev
    Next
    INDEX
    Explanations

    the word "same," sometimes in the context of differences or comparison

    oai_token-act-pair · gemini-2.0-flash

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     admixture
    -0.73
     Hadrian
    -0.60
     Phry
    -0.56
     GTR
    -0.54
     adjournment
    -0.53
     Conſ
    -0.52
     diverti
    -0.52
    פרט
    -0.52
    middag
    -0.49
     Perſ
    -0.49
    POSITIVE LOGITS
    ReusableCell
    0.91
    titleMargin
    0.82
     disambiguazione
    0.78
     كومونز
    0.74
    IsMutable
    0.73
     gynhyrchwyd
    0.68
    %")
    0.68
    paedia
    0.65
     either
    0.65
    Portale
    0.65
    Activations Density 0.741%

    No Known Activations