© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201113
    Prev
    Next
    INDEX
    Explanations

    amplifying signal or potential

    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_12_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
     narcot
    0.60
    ్రహ
    0.59
     slotted
    0.57
     fenced
    0.56
     prescriptive
    0.56
    毋
    0.55
     conduce
    0.54
     constriction
    0.54
     retracted
    0.54
     constricted
    0.54
    POSITIVE LOGITS
    v
    0.79
    n
    0.73
    games
    0.61
    yscrapers
    0.61
    Us
    0.60
    lin
    0.59
     اختلافات
    0.58
    Cl
    0.57
    Games
    0.57
    K
    0.57
    Activations Density 0.001%

    No Known Activations