© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89792
    Prev
    Next
    INDEX
    Explanations

    Kiasu, Kiasi, Krashen, Krasnoyarsk, Krasnaya

    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
    я
    0.81
    ї
    0.70
    し
    0.70
    ки
    0.65
    ین
    0.64
    و
    0.64
    jší
    0.64
    ו
    0.64
    އ
    0.62
    ని
    0.60
    POSITIVE LOGITS
     Kindern
    0.74
    dN
    0.69
     culto
    0.66
     plików
    0.65
    드를
    0.65
    。
    0.63
    ።
    0.63
     voiture
    0.61
    dą
    0.61
    ্থ
    0.60
    Activations Density 0.002%

    No Known Activations