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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261434
    Prev
    Next
    INDEX
    Explanations

    Net-, Het-, Nema, nethack

    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
     in
    1.18
    ك
    1.01
    ка
    0.93
     reicht
    0.91
    ндо
    0.91
    ת
    0.89
     entw
    0.88
    লে
    0.87
    geht
    0.87
    gående
    0.87
    POSITIVE LOGITS
    t
    1.23
    다
    1.16
    นี้
    1.13
    ق
    1.09
                    
    1.09
    ี
    1.08
     presiden
    1.07
    ס
    1.07
    k
    1.06
    ことを
    1.04
    Activations Density 0.000%

    No Known Activations