© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 91868
    Prev
    Next
    INDEX
    Explanations

    safety and protection equipment

    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_11_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
     woning
    0.39
     Irrigation
    0.38
     Pflege
    0.38
     Plumbing
    0.37
     Szer
    0.36
     Housing
    0.36
     Insulation
    0.36
    髹
    0.36
    攽
    0.35
    暐
    0.35
    POSITIVE LOGITS
    ):
    0.36
     \
    0.36
    que
    0.34
    ec
    0.31
     poisoned
    0.30
    ).
    0.30
    ing
    0.29
     que
    0.29
     logistical
    0.29
    :
    0.28
    Activations Density 0.037%

    No Known Activations