© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53382
    Prev
    Next
    INDEX
    Explanations

    URLs with numeric paths

    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_30_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
    henko
    0.41
    বিত
    0.40
     ಬೆ
    0.39
    ográficas
    0.37
    UIT
    0.37
    литься
    0.35
    ǔ
    0.35
    play
    0.35
    ijken
    0.35
    ច្រើន
    0.34
    POSITIVE LOGITS
     eaters
    0.38
    ήμερα
    0.37
     donnant
    0.36
     ghe
    0.36
     czyli
    0.36
     iaitu
    0.35
     gyn
    0.35
     gynec
    0.35
     给
    0.35
     plum
    0.34
    Activations Density 0.001%

    No Known Activations