© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42773
    Prev
    Next
    INDEX
    Explanations

    stro, Ice Cream, cash withdrawal, Pop Culture, 发热, shirt

    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_22_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
    íč
    0.38
    켄
    0.37
     hä
    0.36
    ቦች
    0.33
     samo
    0.33
     ర
    0.33
    术
    0.32
     *-
    0.32
     masy
    0.32
     szt
    0.32
    POSITIVE LOGITS
     сидя
    0.36
    ?),
    0.36
    noindent
    0.33
     vivant
    0.32
     siting
    0.32
     живу
    0.32
     sited
    0.32
    !),
    0.32
     standing
    0.31
    ?).
    0.31
    Activations Density 0.045%

    No Known Activations