© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193995
    Prev
    Next
    INDEX
    Explanations

    example

    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_27_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
     পৌঁ
    0.38
     (’
    0.37
    
    0.35
    έχ
    0.34
    oush
    0.34
    ◻
    0.33
    ՛
    0.32
    
    0.32
    ట్స్‌
    0.31
    ُوْ
    0.31
    POSITIVE LOGITS
    https
    0.40
     https
    0.39
     vede
    0.38
     correr
    0.38
     potem
    0.38
     pernicious
    0.38
     dagger
    0.37
     Fot
    0.36
     شوف
    0.36
     rollup
    0.36
    Activations Density 0.021%

    No Known Activations