© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132453
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     I
    1.10
    জ
    1.02
    は
    1.02
    ی
    1.00
    のこと
    0.99
    d
    0.98
    ના
    0.97
    I
    0.95
     زمینه
    0.93
    ิ
    0.92
    POSITIVE LOGITS
     for
    1.10
    ic
    1.08
    <
    0.92
    iet
    0.92
    uv
    0.91
    mö
    0.90
    mittel
    0.89
    for
    0.89
     ön
    0.88
    0.88
    Activations Density 0.000%

    No Known Activations