© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134844
    Prev
    Next
    INDEX
    Explanations

    stretches

    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_1_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
    ンの
    1.04
    ے
    1.02
    I
    0.97
     commotion
    0.96
    kannya
    0.96
    スの
    0.95
     două
    0.95
    ación
    0.94
    ालय
    0.93
     trellis
    0.93
    POSITIVE LOGITS
    f
    1.79
    an
    1.74
    a
    1.54
    et
    1.40
    ر
    1.37
    ه
    1.35
     for
    1.30
    ar
    1.26
    ج
    1.24
    ى
    1.23
    Activations Density 0.000%

    No Known Activations