© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18347
    Prev
    Next
    INDEX
    Explanations

    positive exclamation followed by noun

    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
    초
    0.46
     отлич
    0.45
     Jenny
    0.39
     excellent
    0.38
     artisanal
    0.38
    뛰
    0.38
     enough
    0.38
     राइट
    0.38
     excelente
    0.37
    ജ്യ
    0.37
    POSITIVE LOGITS
    Stabilise
    0.37
    ALLOC
    0.36
    看一下
    0.36
    ﹰ
    0.35
     analysed
    0.35
     adequacy
    0.35
     پوچھ
    0.35
     plain
    0.35
    anguages
    0.34
    膚
    0.34
    Activations Density 0.010%

    No Known Activations