© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200769
    Prev
    Next
    INDEX
    Explanations

    tenderness to touch or palpation

    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_12_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
     thicken
    0.57
    匽
    0.54
     органы
    0.50
    ским
    0.50
    А
    0.50
     Gosudarstvennyj
    0.50
    नंतर
    0.49
    '`--'`--
    0.48
     त्यानंतर
    0.48
    າກ
    0.47
    POSITIVE LOGITS
     You
    0.57
    Count
    0.54
    bling
    0.53
    ę
    0.49
    ↵↵
    0.46
     Plaintiff
    0.46
    जिटिव
    0.46
     I
    0.46
    Listing
    0.46
     q
    0.46
    Activations Density 0.000%

    No Known Activations