© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89150
    Prev
    Next
    INDEX
    Explanations

    Una

    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_60_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
     vez
    1.98
     times
    1.73
    vez
    1.62
    때
    1.55
     Vez
    1.52
     때
    1.38
     fois
    1.36
     veces
    1.19
     vezes
    1.11
    times
    1.08
    POSITIVE LOGITS
     el
    0.38
     vừa
    0.37
     hine
    0.37
    aille
    0.37
     appena
    0.36
    Timeout
    0.35
    ările
    0.35
    ドウ
    0.34
     ð
    0.33
    ගේ
    0.32
    Activations Density 0.001%

    No Known Activations