© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200549
    Prev
    Next
    INDEX
    Explanations

    made by hand

    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
    '
    1.07
     viscosity
    0.86
     malicious
    0.84
     of
    0.83
     τα
    0.81
     lenguaje
    0.81
    ‘
    0.80
     compressive
    0.79
     speculation
    0.77
     postcode
    0.77
    POSITIVE LOGITS
    an
    1.45
    ار
    1.25
    ان
    1.23
    ar
    1.15
    ন
    1.15
    in
    1.08
    are
    1.06
    f
    1.06
    0
    0.99
    ু
    0.96
    Activations Density 0.000%

    No Known Activations