© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1350
    Prev
    Next
    INDEX
    Explanations

    Behance, Beholder, BEA, behave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     prova
    0.40
    乙
    0.36
     prove
    0.36
    Prove
    0.36
    ⁽
    0.36
    vak
    0.35
    мулятор
    0.35
     Serve
    0.35
    ermek
    0.35
     vacate
    0.34
    POSITIVE LOGITS
    ='%
    0.38
     relent
    0.36
     процент
    0.36
    Be
    0.36
    ="%
    0.35
    fileID
    0.35
    栉
    0.35
     Continuation
    0.35
    蒸
    0.35
    ','%
    0.34
    Activations Density 0.002%

    No Known Activations