© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85624
    Prev
    Next
    INDEX
    Explanations

    cockney, cuckold, Hockney

    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
     aprovechar
    0.72
    오
    0.64
     όπου
    0.61
     gă
    0.59
    ალა
    0.59
    ए
    0.59
    이지만
    0.58
    おそらく
    0.57
     ruộng
    0.56
     podríamos
    0.56
    POSITIVE LOGITS
     are
    0.88
    j
    0.77
    et
    0.75
    ag
    0.73
    lw
    0.73
    eli
    0.71
    p
    0.71
    4
    0.66
    he
    0.64
    ract
    0.64
    Activations Density 0.000%

    No Known Activations