© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157654
    Prev
    Next
    INDEX
    Explanations

    work

    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_50_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
     ++
    0.39
     американ
    0.37
     Dew
    0.36
    amerikan
    0.35
     അമേരിക്ക
    0.35
    Tim
    0.34
    დი
    0.34
     amerikan
    0.34
     miserably
    0.34
     (++
    0.34
    POSITIVE LOGITS
     hacia
    0.70
     towards
    0.69
     toward
    0.64
    towards
    0.62
    Towards
    0.61
     verso
    0.59
     Toward
    0.56
    Toward
    0.56
     Towards
    0.54
     menuju
    0.52
    Activations Density 0.002%

    No Known Activations