© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196813
    Prev
    Next
    INDEX
    Explanations

    wholesale

    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_9_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
    ات
    0.89
    et
    0.88
    ק
    0.84
    ک
    0.77
    in
    0.75
     grupos
    0.72
    ש
    0.71
     keber
    0.70
    }];
    0.69
    ช่วง
    0.69
    POSITIVE LOGITS
     of
    0.89
    (
    0.88
    ри
    0.86
    the
    0.75
    \<
    0.72
    &
    0.71
    )(
    0.71
    <0x97>
    0.69
    CT
    0.69
    和
    0.69
    Activations Density 0.001%

    No Known Activations