© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18838
    Prev
    Next
    INDEX
    Explanations

    espresso

    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_15_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
    川
    0.52
    –
    0.51
     –
    0.47
    Ｕ
    0.46
    おく
    0.46
     동물
    0.44
    設備の
    0.44
    オイル
    0.43
    当地
    0.43
    DFS
    0.42
    POSITIVE LOGITS
     birinci
    0.52
     odont
    0.52
     ogr
    0.49
    只好
    0.49
     soared
    0.49
    犾
    0.49
    頖
    0.49
     rider
    0.49
     করিতেন
    0.49
     bruises
    0.48
    Activations Density 0.002%

    No Known Activations