© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124874
    Prev
    Next
    INDEX
    Explanations

    Cirque du Soleil, Gavarnie, Biohazard

    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
    c
    0.71
    ت
    0.70
    t
    0.67
     Durable
    0.65
    ي
    0.65
    ↵
    0.64
     Polish
    0.62
    शीर
    0.62
    i
    0.61
     Particle
    0.60
    POSITIVE LOGITS
    ną
    0.81
     as
    0.78
     diagnosing
    0.69
    nac
    0.69
     by
    0.63
    nymi
    0.61
     propias
    0.60
    な
    0.60
     लेकर
    0.60
    ३
    0.59
    Activations Density 0.000%

    No Known Activations