© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41671
    Prev
    Next
    INDEX
    Explanations

    Bielefeld, Biela

    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_3_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
    ן
    0.99
    ش
    0.82
    ن
    0.77
    ר
    0.76
    กฎ
    0.69
    ビット
    0.66
    _/
    0.66
     сообщение
    0.64
    า
    0.64
    ರ
    0.64
    POSITIVE LOGITS
    ↵
    0.84
    ca
    0.76
     .
    0.64
    cid
    0.60
    きました
    0.58
     a
    0.56
    chen
    0.55
    ki
    0.55
    Ev
    0.55
    can
    0.54
    Activations Density 0.003%

    No Known Activations