© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33445
    Prev
    Next
    INDEX
    Explanations

    follow

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ನಿರ್
    0.45
     Lý
    0.45
     किल
    0.45
     вмі
    0.42
     Lyman
    0.38
    ನಿರ್
    0.38
    恜
    0.38
    􀂾
    0.37
    刓
    0.36
    傌
    0.36
    POSITIVE LOGITS
    Follow
    1.35
     Follow
    1.34
    follow
    1.30
     follow
    1.29
     follows
    1.23
     FOLLOW
    1.19
    FOLLOW
    1.14
    follows
    1.09
    フォロー
    1.09
    ollow
    1.02
    Activations Density 0.009%

    No Known Activations