© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246077
    Prev
    Next
    INDEX
    Explanations

    early science fiction and comics

    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_40_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
     чита
    0.77
     đọc
    0.75
     lettura
    0.74
     read
    0.72
    讀
    0.71
     reading
    0.71
     leitura
    0.70
    读
    0.69
    読
    0.69
     readership
    0.68
    POSITIVE LOGITS
     early
    0.54
    早
    0.54
    early
    0.49
     EARLY
    0.47
     Early
    0.46
    Early
    0.46
     earliest
    0.44
     早
    0.42
    gun
    0.41
    浄
    0.40
    Activations Density 0.003%

    No Known Activations