© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81483
    Prev
    Next
    INDEX
    Explanations

    impossible or img

    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_0_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
    st
    1.78
    us
    1.73
    ’
    1.58
    ک
    1.52
    isub
    1.45
    is
    1.37
    ৭
    1.33
    isr
    1.30
    нном
    1.22
    '
    1.20
    POSITIVE LOGITS
    0
    1.52
    ش
    1.34
    ق
    1.30
    ;
    1.22
    ้
    1.14
    ح
    1.12
    ח
    1.07
    صور
    1.04
    شل
    1.04
    话
    1.03
    Activations Density 0.001%

    No Known Activations