© 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. 36311
    Prev
    Next
    INDEX
    Explanations

    khaki and hackathon

    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
    0.88
    se
    0.77
    N
    0.77
    jų
    0.76
    B
    0.75
    কথা
    0.74
    З
    0.74
    F
    0.73
    T
    0.73
    ve
    0.73
    POSITIVE LOGITS
    0
    0.72
     deniz
    0.64
     kaki
    0.64
     volonté
    0.64
     sere
    0.64
     cor
    0.63
     l
    0.62
     серь
    0.62
     e
    0.61
     scuola
    0.61
    Activations Density 0.000%

    No Known Activations