© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78464
    Prev
    Next
    INDEX
    Explanations

    product details

    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_29_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
    লো
    0.44
     सर्क
    0.42
     вернуть
    0.38
     จง
    0.37
    ویزی
    0.36
     wysoko
    0.36
    และความ
    0.36
    ])$
    0.36
     ∈
    0.35
     Verbesser
    0.35
    POSITIVE LOGITS
    orduk
    0.39
     paraffin
    0.36
    ெடு
    0.35
     taken
    0.34
    keydown
    0.34
     parede
    0.34
     fantástico
    0.34
     Egg
    0.33
     অক্ষরে
    0.33
     occupied
    0.33
    Activations Density 0.000%

    No Known Activations