© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 206550
    Prev
    Next
    INDEX
    Explanations

    briefly

    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
     fairly
    0.46
    Lapangan
    0.38
    ❚
    0.38
    Eh
    0.36
    Tah
    0.35
    Hear
    0.35
    ThemeOverlay
    0.33
    Seite
    0.33
    yfikacja
    0.32
     〔
    0.32
    POSITIVE LOGITS
     mostrando
    0.69
     cercando
    0.63
     present
    0.62
     showing
    0.61
     Какие
    0.60
     presentando
    0.58
     explicando
    0.57
     explaining
    0.57
     displaying
    0.57
     outlining
    0.57
    Activations Density 0.004%

    No Known Activations