© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58202
    Prev
    Next
    INDEX
    Explanations

    vector

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    );*/
    0.44
     /,
    0.43
    </blockquote>
    0.42
    /.
    0.40
     /.
    0.39
     ~/
    0.39
    iling
    0.38
     "\\
    0.37
    </em>
    0.37
     //.
    0.37
    POSITIVE LOGITS
    ែម
    0.46
    también
    0.45
     Também
    0.43
    P
    0.42
    Training
    0.41
    Positive
    0.41
    Also
    0.41
     també
    0.39
     también
    0.39
     juga
    0.39
    Activations Density 0.001%

    No Known Activations