© 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. 10625
    Prev
    Next
    INDEX
    Explanations

    code snippets, educational text, or biblical text, depending on the context it sees those phrases in.

    oai_token-act-pair · gemini-2.0-flash

    pronouns

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

    pronouns

    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
     Оно
    -0.98
     которое
    -0.97
     яке
    -0.89
     fallu
    -0.80
     doubtnut
    -0.79
    ")->
    -0.78
    Билгалдахарш
    -0.77
    ')->
    -0.73
    setVerticalGroup
    -0.69
    haraan
    -0.69
    POSITIVE LOGITS
     she
    2.80
     her
    2.56
     he
    2.48
     his
    2.39
     him
    2.38
    she
    1.98
    彼は
    1.92
     hers
    1.79
     He
    1.76
     egli
    1.76
    Activations Density 7.626%

    No Known Activations