© 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. 162415
    Prev
    Next
    INDEX
    Explanations

    ask for

    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
     финансовых
    0.63
     금액
    0.57
     돈
    0.54
     dinero
    0.54
    お金
    0.53
    돈
    0.52
     ಹಣ
    0.52
    料金
    0.51
     keuangan
    0.49
    💶
    0.49
    POSITIVE LOGITS
     Griffith
    0.40
    aptan
    0.37
     dr
    0.36
     structural
    0.35
     logistical
    0.34
     estructural
    0.34
    od
    0.34
     labor
    0.34
     Structural
    0.34
     Deliver
    0.34
    Activations Density 0.067%

    No Known Activations