© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 44008
    Prev
    Next
    INDEX
    Explanations

    Fiora, Fiare, Fiasch

    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
     fus
    0.75
    ल
    0.75
     the
    0.74
     reassuring
    0.73
    u
    0.73
     up
    0.70
     fuse
    0.70
    و
    0.68
     foreshadow
    0.67
     wed
    0.66
    POSITIVE LOGITS
    personas
    0.79
    notas
    0.77
    t
    0.75
     Лига
    0.73
    stats
    0.71
    tica
    0.71
    𝕄
    0.70
    Psi
    0.69
    Dining
    0.66
    stable
    0.66
    Activations Density 0.000%

    No Known Activations