© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158320
    Prev
    Next
    INDEX
    Explanations

    wargames

    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
    I
    1.14
    ти
    1.12
    ер
    1.02
    EL
    0.94
    at
    0.91
    ert
    0.89
    る
    0.87
     ожида
    0.84
    ER
    0.84
    ंनी
    0.82
    POSITIVE LOGITS
     VOICE
    0.91
    ことを
    0.90
     sieve
    0.90
     philosopher
    0.86
     sanitized
    0.86
    s
    0.86
     chandelier
    0.85
     brownish
    0.84
    ార్క్
    0.82
     policeman
    0.82
    Activations Density 0.000%

    No Known Activations