© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207792
    Prev
    Next
    INDEX
    Explanations

    Science Focus Magazine

    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_20_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
     Ma
    0.43
     zwei
    0.43
     Besitz
    0.42
    lé
    0.41
    仮
    0.41
    azität
    0.40
    ².
    0.40
    钺
    0.40
     줄
    0.39
    ๒
    0.39
    POSITIVE LOGITS
    危机
    0.48
    GOR
    0.45
     headquarters
    0.44
    DICTION
    0.43
    震惊
    0.42
    ಕ್ಕ
    0.42
    ,_
    0.42
     घोटाले
    0.42
    োজন
    0.42
     Darby
    0.42
    Activations Density 0.000%

    No Known Activations