© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45868
    Prev
    Next
    INDEX
    Explanations

    deal announcement

    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_10_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
    ine
    0.38
    ين
    0.37
    >
    0.37
    ig
    0.36
    ',
    0.33
    ac
    0.33
    ahanglan
    0.33
    <
    0.33
    <0x80>
    0.32
     acid
    0.32
    POSITIVE LOGITS
    3
    0.46
    י
    0.38
    4
    0.37
    Caso
    0.35
    ﻙ
    0.35
     caching
    0.34
     treinta
    0.34
    MktCap
    0.34
    то
    0.33
    کول
    0.33
    Activations Density 0.003%

    No Known Activations