© 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. 141110
    Prev
    Next
    INDEX
    Explanations

    automation scripts

    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
     bean
    0.55
     shu
    0.55
     vaikka
    0.55
    墘
    0.54
     ký
    0.54
     revolver
    0.54
     ovog
    0.54
     volledig
    0.54
     perkara
    0.53
     pigeon
    0.52
    POSITIVE LOGITS
    I
    0.69
     समाचार
    0.63
     I
    0.61
     that
    0.57
    ct
    0.55
    that
    0.55
    rer
    0.55
    Ret
    0.54
     আশ্বাস
    0.52
    Are
    0.52
    Activations Density 0.000%

    No Known Activations