© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29177
    Prev
    Next
    INDEX
    Explanations

    directive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ik
    0.13
    AN
    0.13
    ла
    0.13
     değildir
    0.12
    ος
    0.12
    <0x80>
    0.12
     vincul
    0.12
    ap
    0.12
    yb
    0.12
     morate
    0.11
    POSITIVE LOGITS
     as
    0.15
    로
    0.13
    ^{
    0.12
    lässlich
    0.12
    kurs
    0.12
    駿
    0.12
     उनके
    0.12
    㑓
    0.12
    rayed
    0.12
    lüğ
    0.12
    Activations Density 0.008%

    No Known Activations