© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9258
    Prev
    Next
    INDEX
    Explanations

    check with official sources

    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_13_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
    と同様
    0.44
     manglid
    0.43
    œurs
    0.41
    <unused1071>
    0.41
    iosos
    0.40
    larla
    0.40
    culaire
    0.40
    antiene
    0.40
    chende
    0.39
    actifs
    0.39
    POSITIVE LOGITS
    on
    0.52
    For
    0.44
    Behind
    0.44
    Is
    0.43
    Before
    0.42
    Se
    0.41
    un
    0.40
    ON
    0.39
    K
    0.38
    On
    0.37
    Activations Density 0.274%

    No Known Activations