© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211478
    Prev
    Next
    INDEX
    Explanations

    short notice / for purpose

    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_5_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
    ك
    2.13
    на
    2.00
    ка
    1.86
    스
    1.55
    ку
    1.34
    ের
    1.33
    sız
    1.32
    ی
    1.32
    ת
    1.31
    나
    1.31
    POSITIVE LOGITS
    ok
    1.08
    在一个
    0.98
     Riemannian
    0.96
     Certificate
    0.93
    aturan
    0.93
    可以看到
    0.93
    ty
    0.93
     For
    0.91
    urring
    0.91
    ot
    0.90
    Activations Density 0.000%

    No Known Activations