© 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. 53608
    Prev
    Next
    INDEX
    Explanations

    taken, Organization, individuals, player

    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
    佳
    0.38
    fill
    0.35
    pre
    0.34
    antwort
    0.34
    ertet
    0.34
    Boris
    0.34
     aisa
    0.33
    weixin
    0.33
    PRE
    0.33
    stead
    0.32
    POSITIVE LOGITS
    औ
    0.37
    ёл
    0.34
     исследования
    0.33
     StringBuffer
    0.33
    রাম
    0.32
    연구
    0.31
     рису
    0.31
     Atkins
    0.31
     จึง
    0.31
     jobNumber
    0.31
    Activations Density 0.000%

    No Known Activations