© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28028
    Prev
    Next
    INDEX
    Explanations

    loading functions

    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_40_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
    Rel
    0.38
     czasie
    0.38
    har
    0.37
     хар
    0.37
    ))+\
    0.36
    ソール
    0.35
    ాలా
    0.35
    සු
    0.35
    ++];
    0.34
    ₲
    0.34
    POSITIVE LOGITS
    ਾਵ
    0.38
     Patten
    0.38
     intensify
    0.38
    寶
    0.36
     intensidade
    0.36
     أق
    0.36
    attn
    0.35
     fécond
    0.35
     ممالک
    0.35
    盜
    0.35
    Activations Density 0.001%

    No Known Activations