© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123475
    Prev
    Next
    INDEX
    Explanations

    illegal act

    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_3_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
    g
    0.74
    V
    0.65
    not
    0.65
    ni
    0.64
    的全
    0.63
    يل
    0.63
    能
    0.63
    的要求
    0.63
    max
    0.60
    word
    0.60
    POSITIVE LOGITS
     erreur
    0.76
    ك
    0.73
    ری
    0.72
    یم
    0.72
     pals
    0.67
    یه
    0.67
    י
    0.67
     apparence
    0.66
     akses
    0.66
    ف
    0.66
    Activations Density 0.001%

    No Known Activations