© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215333
    Prev
    Next
    INDEX
    Explanations

    offensive language and Cumbria

    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
    u
    1.62
    ла
    1.33
    n
    1.11
    ле
    0.97
    ку
    0.97
    ভ
    0.95
    या
    0.95
    m
    0.93
    ट
    0.88
    يد
    0.87
    POSITIVE LOGITS
    3
    1.33
    5
    1.20
    4
    1.19
    2
    1.18
     by
    1.17
    8
    1.12
    about
    1.09
     about
    1.09
    0
    1.05
    6
    1.02
    Activations Density 0.000%

    No Known Activations