© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140309
    Prev
    Next
    INDEX
    Explanations

    thanks and you

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    тала
    0.38
    akkhati
    0.38
    bant
    0.37
     prisms
    0.35
    ?=
    0.35
    GULD
    0.34
    compress
    0.33
    leaved
    0.33
     እንኳ
    0.33
     tao
    0.33
    POSITIVE LOGITS
     образова
    0.37
    赈
    0.35
    प्पू
    0.35
    ppu
    0.35
    みな
    0.34
     Dain
    0.34
    sourceIP
    0.34
     edu
    0.34
    addSubview
    0.34
     программы
    0.33
    Activations Density 0.000%

    No Known Activations