© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91470
    Prev
    Next
    INDEX
    Explanations

    -int ails, -epy Exception

    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_11_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
    on
    0.50
    yz
    0.50
    ุก
    0.49
    poke
    0.48
     Vargas
    0.48
    <0x80>
    0.47
    yuk
    0.47
     Girona
    0.47
    Jake
    0.47
    HTMLElement
    0.47
    POSITIVE LOGITS
    ä
    0.54
    UTH
    0.53
     impulses
    0.52
     acorns
    0.52
     clouds
    0.51
    müşt
    0.51
     manures
    0.51
     Inheritance
    0.50
    ithmet
    0.50
     acids
    0.50
    Activations Density 0.000%

    No Known Activations