© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168409
    Prev
    Next
    INDEX
    Explanations

    As

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    烦
    0.82
    还
    0.75
    煩
    0.71
    望
    0.68
     还
    0.65
     trouble
    0.64
    還
    0.61
     Trouble
    0.58
     還
    0.56
    부
    0.55
    POSITIVE LOGITS
    Finding
    0.37
    Identifying
    0.36
     leaves
    0.35
    NMR
    0.35
    Mod
    0.35
     मात्रा
    0.34
    摟
    0.34
    zust
    0.34
    Leave
    0.33
     Leaves
    0.33
    Activations Density 0.004%

    No Known Activations