© 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. 39420
    Prev
    Next
    INDEX
    Explanations

    k-pop idol songs

    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
    ่า
    0.76
    ן
    0.67
     manipulations
    0.66
    ی
    0.63
    യിരുന്നു
    0.60
    াধ
    0.60
     "]
    0.60
    nare
    0.60
     prácticas
    0.59
     Inhalt
    0.59
    POSITIVE LOGITS
    ли
    0.91
    S
    0.83
    on
    0.78
    em
    0.75
    个
    0.73
    hers
    0.71
    のは
    0.70
    p
    0.70
    pg
    0.69
    of
    0.67
    Activations Density 0.004%

    No Known Activations