© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139328
    Prev
    Next
    INDEX
    Explanations

    filter feeding

    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_37_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
    appell
    0.43
     Cheyenne
    0.41
     Top
    0.39
     Siamo
    0.38
    桂
    0.38
     Boys
    0.37
     designations
    0.37
     உயர்த்த
    0.37
     siamo
    0.37
     appell
    0.37
    POSITIVE LOGITS
    侃
    0.42
     entering
    0.39
    ťa
    0.39
     وارد
    0.38
    entering
    0.38
     plugging
    0.38
    Creating
    0.38
     terapia
    0.37
     clogging
    0.37
    訲
    0.37
    Activations Density 0.002%

    No Known Activations