© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163878
    Prev
    Next
    INDEX
    Explanations

    shoulder to cry on, listening ear

    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_13_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
     Cue
    0.43
    不说
    0.43
     وهنا
    0.42
     sarebbero
    0.41
    鬻
    0.41
     мы
    0.40
     спи
    0.40
     wikipedia
    0.40
     Цер
    0.40
     Список
    0.40
    POSITIVE LOGITS
    ysl
    0.46
    re
    0.46
    estimates
    0.46
    ম
    0.46
    м
    0.45
    OTT
    0.44
    IGO
    0.43
    hasta
    0.42
    Advice
    0.42
    I
    0.42
    Activations Density 0.004%

    No Known Activations