© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260035
    Prev
    Next
    INDEX
    Explanations

    trading script expert advisors

    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_22_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
    审美
    0.52
     vurg
    0.46
     exemplar
    0.45
     선보
    0.41
    水道
    0.41
    ☓
    0.41
     sinnvoll
    0.41
    fdPar
    0.40
    的重要性
    0.40
    
    0.40
    POSITIVE LOGITS
     Wr
    0.47
     PJ
    0.44
     Parliament
    0.43
    ór
    0.42
    ja
    0.42
     pj
    0.42
     Zr
    0.42
    ced
    0.41
     Tay
    0.41
    zt
    0.41
    Activations Density 0.000%

    No Known Activations