© 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. 130112
    Prev
    Next
    INDEX
    Explanations

    McFly, McMillian, Macondo

    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
     been
    1.66
     were
    1.46
    u
    1.38
    다
    1.35
    و
    1.34
     contacted
    1.32
    3
    1.32
    lara
    1.30
    ו
    1.29
    o
    1.24
    POSITIVE LOGITS
     It
    1.30
    il
    1.16
     If
    1.07
    ट
    1.02
    ਪ
    0.99
    ilat
    0.97
    ί
    0.95
    on
    0.92
    स्
    0.92
    ssl
    0.91
    Activations Density 0.000%

    No Known Activations