© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42782
    Prev
    Next
    INDEX
    Explanations

    legal representation

    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_13_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
    son
    0.52
    abl
    0.51
     कठ
    0.49
    कला
    0.48
    از
    0.48
    cert
    0.47
    :
    0.47
    czą
    0.46
    light
    0.46
    art
    0.45
    POSITIVE LOGITS
    ^{+},
    0.47
     onlar
    0.46
    лил
    0.44
    훙
    0.44
     railing
    0.43
     buildup
    0.43
    )،
    0.43
    ﺀ
    0.42
    )，
    0.42
     பட்
    0.42
    Activations Density 0.000%

    No Known Activations