© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202150
    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_6_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
    も
    1.50
    도
    1.19
    ও
    1.12
    in
    1.01
    在
    1.00
    ை
    0.88
    ină
    0.86
     in
    0.85
     در
    0.85
    ৩
    0.83
    POSITIVE LOGITS
     Xinhua
    1.06
    ()
    0.99
     If
    0.86
     Sprint
    0.86
    tt
    0.84
     Patrick
    0.84
    </sup>
    0.84
     After
    0.83
     Amanda
    0.82
    );
    0.82
    Activations Density 0.000%

    No Known Activations