© 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. 61652
    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
    在
    1.30
    on
    1.18
    のない
    1.18
    ও
    1.18
     in
    1.17
     và
    1.17
    និង
    1.16
    માં
    1.14
    in
    1.11
    arın
    1.10
    POSITIVE LOGITS
     you
    1.20
     as
    1.09
    ного
    1.05
     that
    1.03
    0
    1.03
     Dogg
    1.01
     Kõ
    0.99
    </a>
    0.97
    ant
    0.96
    ॅ
    0.95
    Activations Density 0.000%

    No Known Activations