© 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. 161962
    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
    t
    1.59
    د
    1.36
    k
    1.34
    na
    1.25
    д
    1.19
    s
    1.14
     interno
    1.11
    sh
    1.09
    ye
    1.07
    sG
    1.07
    POSITIVE LOGITS
    .
    1.16
    er
    1.13
     a
    1.04
     virulent
    1.04
    he
    1.03
    iation
    1.03
     deleterious
    1.01
    pathetic
    1.00
    woman
    0.98
    erver
    0.97
    Activations Density 0.000%

    No Known Activations