© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232151
    Prev
    Next
    INDEX
    Explanations

    mixed signals

    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_6_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
    '
    1.39
    ↵
    1.04
    ली
    1.02
    ação
    1.00
    ۹
    0.91
    .
    0.87
    การ
    0.86
    -
    0.86
    ći
    0.85
    ક
    0.85
    POSITIVE LOGITS
    mp
    1.01
    the
    0.94
    sp
    0.91
     Consequences
    0.87
    mn
    0.86
    me
    0.85
    na
    0.85
    ta
    0.79
    typen
    0.79
    mod
    0.78
    Activations Density 0.000%

    No Known Activations