© 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. 141071
    Prev
    Next
    INDEX
    Explanations

    to the maximum extent

    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
    ра
    0.34
    es
    0.30
     ن
    0.28
     약
    0.27
    ς
    0.27
     période
    0.27
    urts
    0.26
    l
    0.26
    em
    0.26
     كم
    0.25
    POSITIVE LOGITS
     Debug
    0.33
    在该
    0.32
    在這個
    0.31
     Premises
    0.31
     Executors
    0.30
     jika
    0.30
     Practices
    0.30
     semuanya
    0.30
     Mistakes
    0.29
     Formatting
    0.29
    Activations Density 0.001%

    No Known Activations