© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236863
    Prev
    Next
    INDEX
    Explanations

    lists of neighbors or graph elements

    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_32_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
     paj
    0.36
     كار
    0.36
     обрабо
    0.34
     Paj
    0.32
     regla
    0.31
    '}}>
    0.30
    氻
    0.30
     예상
    0.30
     meriye
    0.30
    렌
    0.30
    POSITIVE LOGITS
    insula
    0.37
    Overlay
    0.34
     व्हिडी
    0.33
     accessible
    0.33
     intrusive
    0.32
     Momentum
    0.32
    initis
    0.32
    ኮ
    0.31
    lek
    0.31
    ignent
    0.31
    Activations Density 0.005%

    No Known Activations