© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34452
    Prev
    Next
    INDEX
    Explanations

    difference between

    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_7_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
    on
    1.38
    ir
    1.12
    y
    1.08
    to
    1.02
    ar
    1.02
    o
    1.02
    er
    1.00
    il
    0.99
    or
    0.98
    et
    0.97
    POSITIVE LOGITS
    ین
    0.98
    وس
    0.97
    ند
    0.84
    ینگ
    0.82
    ουν
    0.81
     dignissimos
    0.80
    罗马
    0.80
    רו
    0.79
    ান্য
    0.78
    ק
    0.78
    Activations Density 0.006%

    No Known Activations