© 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. 258671
    Prev
    Next
    INDEX
    Explanations

    First: What

    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
     indifferent
    0.31
     sculptor
    0.30
     happier
    0.30
    tu
    0.30
     marked
    0.29
     polyurethane
    0.29
    𝐔
    0.29
    Cu
    0.29
     continuer
    0.29
    hii
    0.29
    POSITIVE LOGITS
     Toutes
    0.37
     Strategies
    0.34
     terlebih
    0.34
     ചേർ
    0.34
     있죠
    0.33
    ially
    0.33
    ırl
    0.32
     બના
    0.32
     Strateg
    0.32
     Öncelikle
    0.31
    Activations Density 0.003%

    No Known Activations