© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52906
    Prev
    Next
    INDEX
    Explanations

    shedding light

    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_31_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
    दारी
    0.36
    venuto
    0.36
     hút
    0.35
    参数向量
    0.35
     vanishes
    0.35
    戴
    0.35
    비스
    0.35
    ঘাত
    0.34
    ervice
    0.34
    态度
    0.34
    POSITIVE LOGITS
     shedding
    0.63
     shed
    0.59
    쉘
    0.59
    shed
    0.55
     Sche
    0.52
     sche
    0.51
    Sche
    0.51
    sche
    0.51
     схема
    0.49
     sheds
    0.47
    Activations Density 0.015%

    No Known Activations