© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12989
    Prev
    Next
    INDEX
    Explanations

    the token "shi"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the string "Shi"

    np_token-act-pair-logits · gpt-4o-mini

    Shi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    riscoll
    -0.41
    ussia
    -0.40
    ве
    -0.39
    zy
    -0.38
     Up
    -0.38
    Structured
    -0.38
     kr
    -0.38
    ush
    -0.38
    label
    -0.38
     Mr
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.88
     TextInputType
    0.77
     ddelweddau
    0.77
    يكب
    0.73
     HasFactory
    0.71
     Signalez
    0.70
    ErrUnexpectedEOF
    0.69
    PostInfinity
    0.66
     AspNetCore
    0.65
     Réponses
    0.64
    Activations Density 0.270%

    No Known Activations