© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230366
    Prev
    Next
    INDEX
    Explanations

    sex

    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_6_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
    ing
    0.89
    ﻦ
    0.89
    EY
    0.73
    yue
    0.72
     transmission
    0.71
    iye
    0.70
    否
    0.68
    gruppe
    0.67
    bate
    0.67
    ление
    0.66
    POSITIVE LOGITS
    ש
    1.27
    ث
    1.05
    )$:
    1.02
    )\
    0.98
    ס
    0.96
    )$
    0.95
    W
    0.94
    л
    0.90
    }\
    0.90
    "]
    0.89
    Activations Density 0.003%

    No Known Activations