© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58697
    Prev
    Next
    INDEX
    Explanations

    prone to

    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_2_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
    in
    1.75
    ۔
    1.52
    '
    1.49
    m
    1.42
    는
    1.42
    是
    1.23
    l
    1.22
    the
    1.20
    a
    1.20
    は
    1.20
    POSITIVE LOGITS
    ,
    1.13
    نه
    1.08
    లు
    1.04
    ро
    0.98
    شی
    0.96
    قه
    0.95
    ல்
    0.94
    ができる
    0.93
    ,【
    0.91
    ShaderType
    0.91
    Activations Density 0.002%

    No Known Activations