© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204025
    Prev
    Next
    INDEX
    Explanations

    funding and investments

    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_25_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
    entgen
    0.19
     malah
    0.18
    ANA
    0.18
     Yaw
    0.18
     Achieving
    0.18
     instituted
    0.18
    𝘨
    0.17
    আমাদের
    0.17
     Lat
    0.17
     achieves
    0.17
    POSITIVE LOGITS
    龐
    0.21
    ଟ
    0.21
     té
    0.21
    ボックス
    0.21
    ൭
    0.20
     ойношот
    0.20
     बॉक्स
    0.20
     సై
    0.19
    畚
    0.19
     സൈ
    0.19
    Activations Density 0.002%

    No Known Activations