© 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. 88293
    Prev
    Next
    INDEX
    Explanations

    Directed by

    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
    .
    0.71
    ו
    0.67
    ため
    0.61
    t
    0.59
    ために
    0.58
    ?
    0.54
    기
    0.54
    倨
    0.53
    ジ
    0.52
    慎
    0.52
    POSITIVE LOGITS
     direktor
    0.87
     директор
    0.85
     направление
    0.84
     director
    0.84
     DIRECTOR
    0.83
    nél
    0.82
     Director
    0.82
    Director
    0.81
     Directed
    0.80
     directeur
    0.79
    Activations Density 0.002%

    No Known Activations