© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158164
    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
    িন
    1.17
    ۰
    1.15
     ও
    1.12
    ে
    1.10
     نے
    1.05
     で
    1.03
    제로
    0.98
     floated
    0.97
     aconteceu
    0.97
    ,
    0.97
    POSITIVE LOGITS
    sh
    1.02
    </h3>
    0.96
    ory
    0.95
    ined
    0.92
    su
    0.91
    ives
    0.91
     It
    0.90
    𝐬
    0.90
    este
    0.89
    aching
    0.88
    Activations Density 0.000%

    No Known Activations