© 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. 107387
    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
    IS
    1.53
    S
    1.43
    O
    1.38
    I
    1.27
    D
    1.23
    F
    1.19
    .
    1.14
     be
    1.13
    M
    1.10
    U
    1.10
    POSITIVE LOGITS
    \
    1.13
    д
    1.13
     noms
    1.09
    л
    1.08
    ани
    1.07
    あまり
    1.03
    ه
    1.02
    ष्ट
    1.00
     divergents
    1.00
    ان
    0.99
    Activations Density 0.000%

    No Known Activations