© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48214
    Prev
    Next
    INDEX
    Explanations

    stages of a process

    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_10_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
    ف
    0.77
    Phase
    0.76
     Stages
    0.75
    Gesch
    0.73
    お金
    0.72
     Phases
    0.71
     Fase
    0.71
     etapa
    0.68
     Phase
    0.67
    Stage
    0.65
    POSITIVE LOGITS
     with
    0.70
    ी
    0.70
    ี
    0.69
    nation
    0.68
    ி
    0.66
    า
    0.66
    ται
    0.63
    ে
    0.63
    itabbam
    0.61
    don
    0.59
    Activations Density 0.010%

    No Known Activations