© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33511
    Prev
    Next
    INDEX
    Explanations

    Canva graphics

    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_7_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
     from
    0.27
    S
    0.27
     o
    0.24
     with
    0.23
    .
    0.22
    .");
    0.22
    0.22
     that
    0.21
     haircut
    0.20
     out
    0.20
    POSITIVE LOGITS
    ب
    0.30
    و
    0.25
    también
    0.25
    те
    0.24
    n
    0.24
    та
    0.23
    ת
    0.23
    تها
    0.23
    ী
    0.22
    ίδ
    0.22
    Activations Density 0.003%

    No Known Activations