© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105587
    Prev
    Next
    INDEX
    Explanations

    injurious effects

    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_1_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
    1.01
    เป็น
    0.97
    h
    0.95
    ри
    0.93
    จะ
    0.92
    ic
    0.90
    ড
    0.89
    v
    0.87
    ە
    0.87
    ション
    0.86
    POSITIVE LOGITS
     at
    1.45
    ين
    1.40
    ă
    1.39
    ę
    1.28
    ED
    1.14
    ą
    1.09
    한
    1.05
     powied
    1.04
    ة
    1.03
    UL
    1.02
    Activations Density 0.001%

    No Known Activations