© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159551
    Prev
    Next
    INDEX
    Explanations

    want / like / whatever they

    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_2_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
    ።
    0.80
    3
    0.75
    。
    0.73
    ।)
    0.68
    ।
    0.64
    ס
    0.61
    。,
    0.59
     گے۔
    0.59
    。)
    0.59
    ।...
    0.58
    POSITIVE LOGITS
    an
    0.74
    at
    0.73
    p
    0.70
    ↵↵↵↵
    0.69
    ↵↵↵
    0.67
    ă
    0.66
    0.64
    0.63
    of
    0.62
    去
    0.60
    Activations Density 0.005%

    No Known Activations