© 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. 108407
    Prev
    Next
    INDEX
    Explanations

    MAX RT

    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
    ↵
    1.83
    も
    1.21
    ס
    1.18
    ও
    1.11
    ל
    1.09
    dır
    1.03
    า
    1.00
    u
    0.97
    0.97
    )$.
    0.96
    POSITIVE LOGITS
    п
    1.16
    park
    1.12
    ping
    1.04
    ka
    0.99
    pas
    0.98
    cio
    0.98
    p
    0.93
    ban
    0.92
    h
    0.92
     maravill
    0.91
    Activations Density 0.002%

    No Known Activations