© 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. 207017
    Prev
    Next
    INDEX
    Explanations

    on

    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
     field
    0.53
    field
    0.50
     Field
    0.48
     FIELD
    0.47
     campo
    0.46
     location
    0.45
    -{\
    0.45
    FIELD
    0.44
     फील्ड
    0.43
    location
    0.42
    POSITIVE LOGITS
    却
    0.41
    卻
    0.40
    参赛
    0.37
    lot
    0.34
    Lot
    0.34
     TRIP
    0.34
    IFUL
    0.34
     About
    0.34
    лятор
    0.34
     de
    0.34
    Activations Density 0.000%

    No Known Activations