© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214812
    Prev
    Next
    INDEX
    Explanations

    plus or

    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
    وم
    1.02
    ’
    1.01
    ingly
    0.99
    係る
    0.98
    g
    0.93
    ined
    0.91
     במ
    0.87
    ول
    0.86
    ability
    0.84
    iness
    0.82
    POSITIVE LOGITS
     and
    1.77
    ні
    1.56
    ン
    1.53
    ي
    1.47
    <0x0D>
    1.32
    ن
    1.31
    л
    1.30
    s
    1.22
    Y
    1.22
    ные
    1.21
    Activations Density 0.000%

    No Known Activations