© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162642
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and brackets

    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_31_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
     triángulos
    0.37
     SOL
    0.36
    +(\
    0.33
    או
    0.33
     explor
    0.33
     ಮತ
    0.32
    探
    0.32
     Ou
    0.32
     corde
    0.32
    サッカー
    0.32
    POSITIVE LOGITS
    ിലേ
    0.38
    ersion
    0.37
    znego
    0.34
    raintree
    0.33
    Vectorizer
    0.33
    rieren
    0.33
    isent
    0.33
    poses
    0.32
     transmissions
    0.32
    éraux
    0.32
    Activations Density 0.001%

    No Known Activations