© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175319
    Prev
    Next
    INDEX
    Explanations

    knitting and purling

    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_20_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
     profitability
    0.45
     moverse
    0.43
     Pob
    0.41
     операции
    0.41
     sostenibilidad
    0.41
    弊
    0.41
     охла
    0.40
     atriz
    0.40
     పరిస్థి
    0.40
     dislocation
    0.39
    POSITIVE LOGITS
     случайно
    0.47
     k
    0.45
    auche
    0.45
    maxValue
    0.45
     meadow
    0.44
     supervisors
    0.42
    ramer
    0.42
    liers
    0.41
     Morel
    0.41
     plate
    0.41
    Activations Density 0.000%

    No Known Activations