© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196011
    Prev
    Next
    INDEX
    Explanations

    keep these secure

    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_4_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
    2
    1.18
    ’
    0.95
    c
    0.93
    ac
    0.87
    ון
    0.86
    $
    0.86
    f
    0.86
    ile
    0.84
    ను
    0.83
    わ
    0.82
    POSITIVE LOGITS
    ை
    0.98
    ı
    0.97
    is
    0.89
     are
    0.88
     crucified
    0.87
     три
    0.87
     trình
    0.86
    ą
    0.85
     सबै
    0.82
     समुद्री
    0.82
    Activations Density 0.000%

    No Known Activations