© 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. 162155
    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
    ي
    1.52
    ل
    1.48
    i
    1.43
    ין
    1.30
    d
    1.26
    л
    1.24
    י
    1.21
    is
    1.20
    el
    1.20
    .
    1.20
    POSITIVE LOGITS
    ו
    1.32
    ى
    1.31
     you
    1.17
    2
    1.13
    াও
    0.98
    m
    0.93
    ту
    0.93
    다
    0.91
    ope
    0.90
    og
    0.89
    Activations Density 0.000%

    No Known Activations