© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133474
    Prev
    Next
    INDEX
    Explanations

    falls or drops

    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_50_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
     strong
    0.79
     Strong
    0.77
    Strong
    0.77
    strong
    0.70
     STRONG
    0.64
    强
    0.63
    強
    0.56
    STRONG
    0.55
     강
    0.55
     putern
    0.52
    POSITIVE LOGITS
    ാനം
    0.48
    iarism
    0.42
     veloc
    0.41
    לט
    0.40
    ancellationToken
    0.38
    Dav
    0.38
     معكم
    0.38
    পক্ষের
    0.38
    DCs
    0.37
     off
    0.37
    Activations Density 0.003%

    No Known Activations