© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93184
    Prev
    Next
    INDEX
    Explanations

    broad strokes

    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_11_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
     published
    0.46
     council
    0.45
     tarafından
    0.45
     database
    0.45
    amb
    0.45
     veya
    0.44
    স্পতিবার
    0.44
    i
    0.44
     vagy
    0.44
     ch
    0.43
    POSITIVE LOGITS
    他に
    0.53
     IntegerValue
    0.49
     ApiException
    0.48
     greed
    0.48
    सद
    0.47
     такую
    0.46
     మా
    0.45
    АСС
    0.45
    䒴
    0.45
    ディオ
    0.44
    Activations Density 0.000%

    No Known Activations