© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110026
    Prev
    Next
    INDEX
    Explanations

    Ivan the Terrible

    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
    K
    1.04
    Y
    1.00
    V
    0.97
    M
    0.92
    Q
    0.91
    ায়
    0.89
    W
    0.88
    F
    0.87
    B
    0.86
    H
    0.85
    POSITIVE LOGITS
    an
    1.48
    ت
    1.41
    ان
    1.37
    a
    1.34
    ه
    1.29
    া
    1.20
    י
    1.17
    et
    1.16
     on
    1.16
    ي
    1.16
    Activations Density 0.000%

    No Known Activations