© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24741
    Prev
    Next
    INDEX
    Explanations

    descriptive word: vibrant, cook, mason, guys, lives

    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_10_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
    ES
    0.98
     are
    0.96
    리
    0.95
    주
    0.93
    ق
    0.92
    CE
    0.86
    MAN
    0.86
    2
    0.85
    DC
    0.85
    OS
    0.83
    POSITIVE LOGITS
     fique
    0.80
     нажмите
    0.79
    ↵
    0.75
     ကျွန်
    0.74
     ပြော
    0.72
     பார்க்கும்
    0.71
     рав
    0.70
     опыта
    0.68
     exuber
    0.68
     воде
    0.68
    Activations Density 0.000%

    No Known Activations