© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127111
    Prev
    Next
    INDEX
    Explanations

    email list

    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_3_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
    i
    1.09
    ي
    1.05
    a
    1.03
    ب
    0.92
    e
    0.82
    n
    0.81
    s
    0.80
    ر
    0.75
    ه
    0.75
    y
    0.75
    POSITIVE LOGITS
    0.63
     to
    0.61
     consola
    0.58
     savoir
    0.57
    actors
    0.57
    ico
    0.57
    ando
    0.57
     تا
    0.56
     وجود
    0.56
     ይህም
    0.55
    Activations Density 0.000%

    No Known Activations