© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215346
    Prev
    Next
    INDEX
    Explanations

    mom or mother

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     부
    0.70
     떨
    0.64
    떨
    0.61
    こ
    0.52
     बु
    0.49
    কো
    0.48
    꼬
    0.47
     Bu
    0.46
     Бу
    0.46
    actos
    0.46
    POSITIVE LOGITS
     Ark
    0.47
    Ark
    0.46
     Mom
    0.45
     mum
    0.43
     mom
    0.43
    Mom
    0.43
     Mam
    0.42
    まま
    0.41
    mam
    0.40
    mama
    0.40
    Activations Density 0.000%

    No Known Activations