© 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
    2. Gemma-3-27B-IT
    3. 7-GEMMASCOPE-2-TRANSCODER-262K
    4. 32844
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    N
    0.53
    )//
    0.48
     bullets
    0.48
    ’.
    0.48
     expansions
    0.47
    ’,
    0.46
    ’:
    0.45
    ותו
    0.45
     tubers
    0.44
     insulin
    0.43
    POSITIVE LOGITS
    թ
    0.55
    粛
    0.54
    主演
    0.52
    addKill
    0.52
     жовт
    0.52
    Ꮏ
    0.51
     Probation
    0.50
    鳶
    0.50
    嘖
    0.50
    ハー
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.