© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147968
    Prev
    Next
    INDEX
    Explanations

    P abbreviations

    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_59_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
     п
    0.44
     प
    0.40
    ป
    0.39
    ペ
    0.39
     پ
    0.38
     พ
    0.38
    п
    0.36
     প
    0.35
     पि
    0.34
    менти
    0.33
    POSITIVE LOGITS
     PR
    2.09
     PA
    1.76
    PR
    1.74
     PL
    1.62
     PH
    1.58
     PE
    1.53
    PA
    1.44
     PO
    1.39
     PF
    1.38
     PS
    1.37
    Activations Density 0.028%

    No Known Activations