© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201579
    Prev
    Next
    INDEX
    Explanations

    provolone, mail, Pass

    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_6_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
    V
    1.24
    B
    1.19
    ב
    1.13
     on
    1.11
    J
    1.07
    on
    1.05
    ו
    1.04
    ס
    1.02
     to
    0.99
    ↵↵
    0.93
    POSITIVE LOGITS
    ividade
    0.93
    ziff
    0.89
     Sagittarius
    0.87
    vorschau
    0.86
     Titanic
    0.86
     Дэ
    0.84
     Наи
    0.83
     Drinfeld
    0.82
     Акаде
    0.82
    vention
    0.80
    Activations Density 0.000%

    No Known Activations