© 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. 46853
    Prev
    Next
    INDEX
    Explanations

    trinitrotoluene

    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
    '
    0.92
    ל
    0.88
    ā
    0.80
    し
    0.77
     (
    0.75
    ás
    0.73
    ietic
    0.71
    omorphic
    0.69
    ävä
    0.69
    मध्ये
    0.66
    POSITIVE LOGITS
    ের
    1.06
    s
    0.75
    šky
    0.68
    0
    0.68
    ﺔ
    0.68
     %).
    0.67
    েরা
    0.64
    ка
    0.63
    }=
    0.63
    эль
    0.63
    Activations Density 0.000%

    No Known Activations