© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154997
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    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_60_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
     plan
    0.39
     conceit
    0.35
    プラン
    0.35
    SDD
    0.35
     meyd
    0.34
    腹
    0.34
     wardrobe
    0.34
     والأ
    0.33
     shoreline
    0.33
     fourteenth
    0.33
    POSITIVE LOGITS
     II
    2.02
    II
    1.75
     III
    1.73
    III
    1.66
     ii
    1.48
    Ⅱ
    1.26
     iii
    1.25
    ii
    1.11
    Ⅲ
    1.06
     IV
    1.03
    Activations Density 0.001%

    No Known Activations