© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141375
    Prev
    Next
    INDEX
    Explanations

    world travels

    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_12_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
     cinese
    0.56
     Nhật
    0.52
    modell
    0.52
     passeio
    0.52
     ξεκ
    0.52
     fragen
    0.51
     ά
    0.49
     gefunden
    0.49
     modell
    0.49
     öner
    0.49
    POSITIVE LOGITS
     discrimin
    0.54
    ل
    0.54
    resolve
    0.53
    त्
    0.52
    শীল
    0.52
    תי
    0.50
    ربة
    0.50
    KBr
    0.50
    *
    0.49
    ല
    0.48
    Activations Density 0.000%

    No Known Activations