© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169385
    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_56_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
     th
    0.39
    ths
    0.39
    lüsse
    0.38
     thuring
    0.37
    ␣
    0.37
    strawberry
    0.37
    ellidos
    0.36
    ㄜ
    0.36
    KK
    0.36
    enges
    0.36
    POSITIVE LOGITS
     laying
    0.43
     lay
    0.43
     pu
    0.43
     পু
    0.41
     पु
    0.40
     par
    0.40
    рея
    0.40
     common
    0.38
    ியே
    0.38
     p
    0.38
    Activations Density 0.000%

    No Known Activations