© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15926
    Prev
    Next
    INDEX
    Explanations

    negative assignments

    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_34_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
     оборо
    0.37
     senare
    0.36
    overwrite
    0.35
     بسته
    0.35
     melt
    0.34
    ధ
    0.34
     resiliency
    0.34
     영상
    0.33
     resilient
    0.33
    ვ
    0.33
    POSITIVE LOGITS
    =-
    0.53
    Negative
    0.49
     [-
    0.48
     (-
    0.47
    [-
    0.45
     negative
    0.45
     отрица
    0.45
    ([-
    0.44
     Negative
    0.43
    }=-
    0.43
    Activations Density 0.067%

    No Known Activations