© 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. 243548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    icksburg
    0.43
    complexity
    0.39
    Parameteri
    0.38
    ложении
    0.38
    <0x96>
    0.37
    nde
    0.36
     ಪದ
    0.36
    Shelf
    0.35
    に入れる
    0.35
     Lords
    0.34
    POSITIVE LOGITS
     out
    0.41
    出來
    0.40
    出来
    0.40
    ष्टि
    0.38
     trajectories
    0.38
     专业
    0.37
    轨迹
    0.37
    chev
    0.35
     lookout
    0.35
     優
    0.35
    Activations Density 0.001%

    No Known Activations