© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201838
    Prev
    Next
    INDEX
    Explanations

    second one

    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_6_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
     It
    1.19
     I
    1.09
    й
    1.05
    ı
    1.05
     stellt
    0.90
     For
    0.87
     rimane
    0.87
     první
    0.86
    UM
    0.86
    в
    0.85
    POSITIVE LOGITS
    s
    1.29
    9
    1.24
    al
    1.12
    8
    1.08
    6
    1.05
    ل
    1.02
    4
    1.00
    5
    0.98
    ता
    0.96
    7
    0.95
    Activations Density 0.000%

    No Known Activations