© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137027
    Prev
    Next
    INDEX
    Explanations

    funny women comedians English

    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_12_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
    0.71
     coincidence
    0.64
     n
    0.59
    V
    0.58
    С
    0.56
    etzten
    0.55
    К
    0.55
     ن
    0.55
    마
    0.55
    𝗖
    0.54
    POSITIVE LOGITS
     sól
    0.54
    дек
    0.54
     sólidos
    0.54
     então
    0.52
     fórmula
    0.51
     problemen
    0.51
     cálculos
    0.50
     entonces
    0.50
     sopa
    0.49
    )])
    0.49
    Activations Density 0.000%

    No Known Activations