© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42520
    Prev
    Next
    INDEX
    Explanations

    study objectives

    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
    m
    0.71
    理
    0.69
    ق
    0.66
    L
    0.66
    س
    0.64
    体
    0.63
    B
    0.63
    ständ
    0.60
    V
    0.59
    S
    0.58
    POSITIVE LOGITS
    та
    0.70
     escalate
    0.68
     criticise
    0.68
     présente
    0.68
     peningkatan
    0.67
    ti
    0.66
     authorise
    0.66
     установлен
    0.66
    0.66
     transportar
    0.66
    Activations Density 0.013%

    No Known Activations