© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212206
    Prev
    Next
    INDEX
    Explanations

    latex formatting and code delimiters

    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_5_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
    .
    1.71
    in
    1.24
    D
    1.13
    지
    1.13
    q
    1.02
     .
    1.02
    ล
    0.98
    ().
    0.96
    라
    0.95
    ות
    0.93
    POSITIVE LOGITS
     instalação
    1.09
     သည်
    1.09
     étudiant
    1.06
    <0x91>
    1.03
     économ
    0.99
    h
    0.98
     Pythag
    0.98
    atthena
    0.98
     équipe
    0.96
     mislead
    0.96
    Activations Density 0.001%

    No Known Activations