© 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. 24612
    Prev
    Next
    INDEX
    Explanations

    held

    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
    찼
    0.38
     করিতেছে
    0.38
     ದಾಖ
    0.37
     runner
    0.36
    mont
    0.34
    榊
    0.33
    runner
    0.33
    उन्
    0.33
     voglia
    0.33
     pasukan
    0.33
    POSITIVE LOGITS
     held
    3.28
    Held
    2.95
    held
    2.91
     Held
    2.88
     برگزار
    1.71
    持
    1.33
     održ
    1.32
    举行
    1.25
     diadakan
    1.25
     gehalten
    1.23
    Activations Density 0.010%

    No Known Activations