© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124602
    Prev
    Next
    INDEX
    Explanations

    Direct Rail Steering

    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_3_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
    _
    1.07
    不僅
    0.75
    不仅
    0.71
    ER
    0.68
    し
    0.68
    ᅴ
    0.68
     revital
    0.66
    ት
    0.64
    in
    0.64
    '،
    0.64
    POSITIVE LOGITS
    re
    0.66
    ่า
    0.66
     scand
    0.61
     summar
    0.60
     to
    0.58
     critic
    0.57
    ์
    0.57
    dos
    0.55
    al
    0.55
     sobres
    0.55
    Activations Density 0.005%

    No Known Activations