© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39081
    Prev
    Next
    INDEX
    Explanations

    Space and spatial concepts

    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
    ৯
    0.81
    м
    0.78
    ون
    0.75
    ాడు
    0.72
    кри
    0.71
    لي
    0.70
    ية
    0.70
    ۹
    0.68
    ৮
    0.66
    ጕ
    0.66
    POSITIVE LOGITS
    I
    0.83
    ।
    0.79
    0
    0.72
    s
    0.71
    。
    0.70
    O
    0.68
    E
    0.63
    ?
    0.62
    rs
    0.61
    ant
    0.60
    Activations Density 0.005%

    No Known Activations