© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58964
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ل
    1.92
    it
    1.46
     to
    1.46
    n
    1.45
    ن
    1.43
    น
    1.42
    m
    1.33
    b
    1.24
    л
    1.24
    ร
    1.22
    POSITIVE LOGITS
    '
    2.44
    \
    1.44
    :
    1.41
    ’
    1.27
    (
    1.20
    '=
    1.16
     точке
    1.10
    ği
    1.08
    '></
    1.05
    ING
    1.02
    Activations Density 0.000%

    No Known Activations