© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253431
    Prev
    Next
    INDEX
    Explanations

    0

    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_56_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
    ‐
    0.47
    -
    0.41
    )-
    0.40
    itioner
    0.37
    ears
    0.37
    -​
    0.37
    ‑
    0.36
    ؍
    0.36
    দের
    0.35
    )=-
    0.35
    POSITIVE LOGITS
    Ist
    0.39
     Yi
    0.39
     ყველ
    0.37
     diferente
    0.37
    不同
    0.36
     Yog
    0.36
     Ist
    0.36
     हट
    0.36
     MOST
    0.36
    孔
    0.36
    Activations Density 0.001%

    No Known Activations