© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50412
    Prev
    Next
    INDEX
    Explanations

    pandas df operations

    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
    ಳೆದ
    0.44
     Newtonian
    0.39
     years
    0.38
     ആവശ്യ
    0.37
    长
    0.37
     Education
    0.37
     Jahrze
    0.36
    ocer
    0.36
     Community
    0.36
     signup
    0.35
    POSITIVE LOGITS
    pyrimidine
    0.41
    ErrMsg
    0.38
    ermos
    0.36
    湪
    0.35
     अनन्या
    0.34
    eningkatan
    0.34
     أعمال
    0.34
     qualité
    0.34
     चम्म
    0.33
    엷
    0.33
    Activations Density 0.000%

    No Known Activations