© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77462
    Prev
    Next
    INDEX
    Explanations

    B

    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_53_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
     savoir
    0.41
     dž
    0.39
    舅
    0.39
     weakened
    0.38
    Pinned
    0.38
     abnorm
    0.37
    Khe
    0.37
     Khe
    0.37
     Marks
    0.37
     risus
    0.37
    POSITIVE LOGITS
    ौल
    0.44
     దో
    0.40
    龚
    0.38
     ஸ்ட
    0.37
    if
    0.37
    YL
    0.36
     tuy
    0.35
    튜
    0.35
    osit
    0.34
    Schmidt
    0.34
    Activations Density 0.008%

    No Known Activations