© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198356
    Prev
    Next
    INDEX
    Explanations

    structured documents

    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_15_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
     Pulse
    0.48
    M
    0.45
    f
    0.44
    товый
    0.44
     फ
    0.44
     Pool
    0.43
     Stone
    0.43
    0
    0.42
    Sh
    0.42
     Flora
    0.42
    POSITIVE LOGITS
     traduction
    0.51
    vergne
    0.51
     इंट्रोडक्शन
    0.50
     laboratoires
    0.50
    ન્ડ
    0.49
     introducción
    0.49
    ᓲ
    0.49
     élevées
    0.49
     rapporte
    0.49
    jpeg
    0.49
    Activations Density 0.000%

    No Known Activations