© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230344
    Prev
    Next
    INDEX
    Explanations

    that last

    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
    ים
    1.30
    s
    1.27
    and
    1.23
     on
    1.09
     for
    1.06
    ों
    1.04
     b
    0.98
    ्स
    0.98
    ட்சத்திர
    0.98
     by
    0.96
    POSITIVE LOGITS
    ه
    1.02
    ように
    0.91
    seite
    0.88
    valuation
    0.88
    a
    0.87
    া
    0.87
    ur
    0.87
    padă
    0.87
    baiki
    0.86
    н
    0.85
    Activations Density 0.004%

    No Known Activations