© 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. 61183
    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
    1.23
     i
    1.16
     a
    1.11
     is
    1.08
     as
    1.02
     โ
    1.02
     be
    0.99
     \
    0.98
     y
    0.95
     tenga
    0.93
    POSITIVE LOGITS
    ri
    1.19
    3
    1.16
    dh
    1.12
    5
    1.11
    ном
    1.10
    ंना
    1.09
    י
    1.08
    6
    1.04
    ק
    1.02
    та
    0.98
    Activations Density 0.000%

    No Known Activations