© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3758
    Prev
    Next
    INDEX
    Explanations

    self-description as a model

    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_39_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
    sendKeyDown
    0.42
     भुव
    0.41
    avec
    0.40
    BigDecimal
    0.40
    ન્યા
    0.40
    豇
    0.39
     وانت
    0.38
     Benutz
    0.38
     verfol
    0.37
     pédicule
    0.37
    POSITIVE LOGITS
     Practice
    0.40
     Asia
    0.40
     Taiwan
    0.39
     Functions
    0.38
     Templates
    0.37
     superpowers
    0.37
     live
    0.37
     हरे
    0.36
    >©
    0.36
     Images
    0.36
    Activations Density 0.172%

    No Known Activations