© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87092
    Prev
    Next
    INDEX
    Explanations

    "tastic"`"`

    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_3_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
    t
    1.05
    AKE
    0.71
     Paperback
    0.70
     Synonym
    0.68
    ')";
    0.66
    }$)
    0.65
    жке
    0.64
    i
    0.63
     économiques
    0.62
    AC
    0.61
    POSITIVE LOGITS
    в
    0.71
     jasa
    0.65
     *=
    0.64
     hizo
    0.63
     lascia
    0.62
     ઊ
    0.62
    с
    0.62
    that
    0.60
    ライン
    0.59
    רי
    0.58
    Activations Density 0.001%

    No Known Activations