© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195137
    Prev
    Next
    INDEX
    Explanations

    transcoding, coding, converting

    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
    ಿಗಳು
    1.03
    ي
    0.98
    ъ
    0.96
    '
    0.89
    י
    0.89
    지
    0.89
    暏
    0.87
    غیر
    0.86
    ض
    0.86
    트
    0.86
    POSITIVE LOGITS
    o
    1.26
    ian
    1.13
    h
    1.08
    g
    1.07
    .
    1.06
    1.02
    ong
    0.98
    you
    0.96
    yr
    0.94
    om
    0.88
    Activations Density 0.000%

    No Known Activations