© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199296
    Prev
    Next
    INDEX
    Explanations

    first-person statements

    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_27_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
    アウト
    0.37
    獵
    0.35
    Expire
    0.34
    Seller
    0.34
    Expiry
    0.34
     গমন
    0.32
     CheckKey
    0.31
    ProjectPath
    0.31
    Trainer
    0.31
     whisper
    0.30
    POSITIVE LOGITS
    ્યાર
    0.39
     deleterious
    0.37
     फोटो
    0.35
    nders
    0.33
     créé
    0.32
    闶
    0.31
     feuille
    0.31
     adversely
    0.31
    ائی
    0.31
     detrimental
    0.31
    Activations Density 0.001%

    No Known Activations