© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9152
    Prev
    Next
    INDEX
    Explanations

    vehicle and road contexts

    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_40_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
    ParallelGroup
    0.38
     പ്രവർത്തന
    0.36
    icago
    0.34
    𝟮
    0.34
    igious
    0.34
     conceito
    0.33
    awanda
    0.33
    フォン
    0.32
    liquer
    0.32
    燗
    0.32
    POSITIVE LOGITS
     pir
    0.35
     ci
    0.34
     Plates
    0.31
     Pir
    0.31
     MV
    0.30
    畄
    0.30
     plates
    0.30
     sup
    0.29
    चौ
    0.29
     గే
    0.29
    Activations Density 0.008%

    No Known Activations