© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44767
    Prev
    Next
    INDEX
    Explanations

    let's clarify/understand

    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_22_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
     vows
    0.29
    捃
    0.28
     ऊ
    0.28
     Being
    0.28
    笉
    0.27
     Extensions
    0.27
     Berechnung
    0.27
    每一个
    0.27
     Strong
    0.26
    హా
    0.26
    POSITIVE LOGITS
    classification
    0.32
    クラス
    0.31
    klass
    0.29
    }.")
    0.29
    rarea
    0.28
    İ
    0.28
     provavelmente
    0.27
     colliding
    0.27
    TOUCH
    0.27
    ству
    0.26
    Activations Density 0.009%

    No Known Activations