© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141625
    Prev
    Next
    INDEX
    Explanations

    loads of

    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_12_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
    '
    0.93
     tax
    0.70
     for
    0.63
    </td>
    0.62
     require
    0.62
     stvarn
    0.60
     bunch
    0.58
     investment
    0.57
    ’
    0.57
     specified
    0.56
    POSITIVE LOGITS
    ام
    0.69
     होतात
    0.58
    ricting
    0.57
    зіно
    0.55
    áme
    0.55
     carreira
    0.55
    нению
    0.54
     الكسور
    0.54
    argb
    0.53
    ándolo
    0.52
    Activations Density 0.000%

    No Known Activations