© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43037
    Prev
    Next
    INDEX
    Explanations

    people counts or numbers

    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_22_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
     erinn
    0.22
    ルコ
    0.22
     nanot
    0.21
     Alec
    0.20
    垁
    0.20
     recalls
    0.19
     рассказывает
    0.19
    まあ
    0.19
     tache
    0.19
    ปก
    0.19
    POSITIVE LOGITS
     Adults
    0.22
     adultos
    0.22
    㐰
    0.22
     هيا
    0.21
    Adult
    0.21
    теря
    0.20
    hôpital
    0.20
    issionais
    0.20
     hospitalization
    0.20
     הא
    0.19
    Activations Density 0.002%

    No Known Activations