© 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. 42360
    Prev
    Next
    INDEX
    Explanations

    black

    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
    the
    1.02
    .
    0.93
    is
    0.92
     for
    0.87
    to
    0.87
    t
    0.84
     the
    0.81
     de
    0.80
    ed
    0.78
     le
    0.78
    POSITIVE LOGITS
    м
    0.82
     എന്നാല്‍
    0.75
    з
    0.73
    хоро
    0.71
    нача
    0.71
    р
    0.70
    что
    0.70
    н
    0.70
    во
    0.68
    без
    0.67
    Activations Density 0.001%

    No Known Activations