© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37744
    Prev
    Next
    INDEX
    Explanations

    aquaculture or specific place names

    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_3_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
     \
    0.83
     a
    0.81
     be
    0.70
    ف
    0.67
    u
    0.66
    me
    0.65
    ز
    0.59
    з
    0.58
    AN
    0.57
     עם
    0.57
    POSITIVE LOGITS
    ות
    0.94
    ור
    0.77
    너지
    0.75
    தி
    0.75
    ’
    0.68
    보다
    0.65
     molyb
    0.65
    宩
    0.65
    이사
    0.64
    }))
    0.64
    Activations Density 0.007%

    No Known Activations