© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81621
    Prev
    Next
    INDEX
    Explanations

    wheelchairs and runways

    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_0_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
    ル
    1.81
    ラ
    1.66
    ;
    1.61
    A
    1.60
     is
    1.48
    л
    1.43
     as
    1.40
    レ
    1.38
    گ
    1.32
    ার
    1.31
    POSITIVE LOGITS
    1
    1.34
    ний
    1.20
    3
    1.19
    ある
    1.12
    ך
    1.08
    ካከል
    1.07
    ب
    1.02
     глава
    1.01
     hielo
    1.00
     treinta
    1.00
    Activations Density 0.000%

    No Known Activations