© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61092
    Prev
    Next
    INDEX
    Explanations

    pop culture characters & media

    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_11_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
    nými
    0.55
    and
    0.50
     موسیقی
    0.50
     stressing
    0.47
    ducers
    0.46
     ειδ
    0.46
    新兴
    0.46
    ङ
    0.45
    with
    0.45
    ran
    0.45
    POSITIVE LOGITS
     Шрифт
    0.54
     আস্থা
    0.54
    정책
    0.53
    CHF
    0.52
     Buen
    0.51
     perempt
    0.51
    펩
    0.51
     compañeros
    0.50
    PPAR
    0.50
     selfless
    0.50
    Activations Density 0.016%

    No Known Activations