© 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. 201793
    Prev
    Next
    INDEX
    Explanations

    clearance, pinch, segment, point, rails

    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
     –
    0.39
     -
    0.39
    belum
    0.38
     overland
    0.37
     planas
    0.35
    _
    0.35
     beautiful
    0.34
     gre
    0.34
     Shalom
    0.33
    ✍
    0.33
    POSITIVE LOGITS
    ссию
    0.41
    جه
    0.40
    قه
    0.39
    ลา
    0.38
    NGTH
    0.38
    ネ
    0.38
     অব
    0.37
    উন
    0.37
    そのような
    0.37
    テイン
    0.37
    Activations Density 0.000%

    No Known Activations