© 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. 170145
    Prev
    Next
    INDEX
    Explanations

    numbers like batch size

    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
     沒有
    0.43
     நுரைய
    0.38
     allowed
    0.38
    ίν
    0.37
     佐
    0.37
     permitted
    0.37
     parada
    0.37
     LTC
    0.37
     เต
    0.37
    霉
    0.37
    POSITIVE LOGITS
     $-
    0.41
    --"
    0.38
    멀
    0.37
    +'/
    0.36
    虹
    0.36
     OO
    0.35
    EnglishMarks
    0.35
    Multi
    0.35
    ჷ
    0.34
    expansive
    0.34
    Activations Density 0.000%

    No Known Activations