© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75845
    Prev
    Next
    INDEX
    Explanations

    Terraform resource definitions

    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_31_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
    }^{+
    0.39
    tochy
    0.39
     toric
    0.39
     kasnije
    0.38
     simplices
    0.38
    ினா
    0.38
     সঙ্কট
    0.37
    ობს
    0.37
    clause
    0.37
     baad
    0.37
    POSITIVE LOGITS
    Bever
    0.46
     रोक
    0.38
     остальные
    0.38
     осве
    0.38
    🍺
    0.38
     Beverly
    0.37
     Beverage
    0.37
     ввод
    0.37
     দাব
    0.36
     декора
    0.36
    Activations Density 0.003%

    No Known Activations