© 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. 236021
    Prev
    Next
    INDEX
    Explanations

    code context abbreviations

    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
     Veränder
    0.36
     запа
    0.35
    禕
    0.35
     Запа
    0.35
    aplan
    0.34
     dibutuhkan
    0.33
    ularis
    0.33
     planar
    0.33
     verbal
    0.32
     unify
    0.32
    POSITIVE LOGITS
     nást
    0.44
    ისა
    0.43
     religión
    0.42
    Surname
    0.41
    éis
    0.41
    íns
    0.41
    🏩
    0.41
     साहित्यिक
    0.41
    NoStop
    0.41
    ドラ
    0.40
    Activations Density 0.004%

    No Known Activations