© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 215024
    Prev
    Next
    INDEX
    Explanations

    rote memorization

    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_16_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
    ายเป็น
    0.55
     поста
    0.48
    牖
    0.48
    ᴄ
    0.47
    瞭
    0.47
     åt
    0.46
     tinct
    0.46
     counteract
    0.46
    𝑚
    0.45
    <0x83>
    0.45
    POSITIVE LOGITS
     repetitive
    0.84
    6
    0.79
    repet
    0.73
     repet
    0.73
     repeating
    0.71
     repetition
    0.69
    repe
    0.67
     repetir
    0.63
     Repeating
    0.63
     recurring
    0.60
    Activations Density 0.005%

    No Known Activations