© 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. 231846
    Prev
    Next
    INDEX
    Explanations

    V8 engine models

    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
    dı
    1.44
    dır
    1.23
    ה
    1.23
    し
    1.13
    d
    1.02
    <0xAF>
    1.01
    ру
    1.00
    daki
    1.00
    dür
    1.00
    drá
    1.00
    POSITIVE LOGITS
    att
    1.08
    ik
    1.03
    iv
    0.95
    ands
    0.91
    _
    0.90
    iva
    0.86
     ongel
    0.86
     เข
    0.85
    ua
    0.78
    ays
    0.77
    Activations Density 0.000%

    No Known Activations