© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123144
    Prev
    Next
    INDEX
    Explanations

    divide and conquer

    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
    的同时
    0.63
    的光
    0.60
    的目标
    0.59
    现
    0.59
    發表
    0.55
     e
    0.55
    玤
    0.54
     Scales
    0.54
     αρχ
    0.53
     עד
    0.53
    POSITIVE LOGITS
    t
    1.24
    0
    0.93
    l
    0.80
    د
    0.79
    an
    0.79
    ه
    0.78
    л
    0.75
    т
    0.75
    ${\
    0.72
    y
    0.70
    Activations Density 0.000%

    No Known Activations