© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200518
    Prev
    Next
    INDEX
    Explanations

    perfect or ideal _

    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_12_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
     boroughs
    0.59
     attempts
    0.55
     bristles
    0.54
     ADA
    0.52
     ACLU
    0.52
     dungeons
    0.52
     aren
    0.52
    <()>
    0.52
     ليست
    0.51
     weakens
    0.50
    POSITIVE LOGITS
    ͅ
    0.59
     descargar
    0.57
    ž
    0.56
     fabricación
    0.55
     convivencia
    0.55
    𝙢
    0.52
    ι
    0.52
     disfrutar
    0.51
     matemático
    0.51
    Fechar
    0.50
    Activations Density 0.001%

    No Known Activations