© 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. 141953
    Prev
    Next
    INDEX
    Explanations

    toggle flip-flop

    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
     ligament
    0.61
    ，
    0.57
    。
    0.57
     ligaments
    0.56
     i
    0.55
     diast
    0.53
     rake
    0.52
     standpoint
    0.52
     sart
    0.52
     copier
    0.52
    POSITIVE LOGITS
    fl
    0.63
    었다
    0.61
    م
    0.59
    म
    0.57
    어
    0.57
     Mereka
    0.56
    ”)
    0.55
    čne
    0.55
    iyorum
    0.54
    ˶
    0.54
    Activations Density 0.002%

    No Known Activations