© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229385
    Prev
    Next
    INDEX
    Explanations

    new life

    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
    (
    0.93
    About
    0.90
    }
    0.90
    AA
    0.89
    UT
    0.86
    MAN
    0.83
    >
    0.81
    Lovely
    0.80
    RE
    0.79
    U
    0.79
    POSITIVE LOGITS
    י
    1.09
    ി
    1.05
     соревнования
    0.96
    。[
    0.95
    ي
    0.93
     периода
    0.92
    ・・・。
    0.91
    ai
    0.91
     comentários
    0.91
    މ
    0.90
    Activations Density 0.000%

    No Known Activations