© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237040
    Prev
    Next
    INDEX
    Explanations

    turned out to be

    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_32_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
    ார்ப
    0.33
    ષા
    0.33
    فع
    0.32
    ऊ
    0.32
    劲
    0.32
     لان
    0.30
    苍
    0.30
    ام
    0.30
     הר
    0.30
     வேளாண்
    0.30
    POSITIVE LOGITS
     became
    0.59
     okaza
    0.55
    became
    0.50
     оказались
    0.49
     turns
    0.48
     becomes
    0.47
     becoming
    0.47
    成为
    0.47
    成為
    0.47
     оказалась
    0.47
    Activations Density 0.001%

    No Known Activations