© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22173
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    હેરા
    0.42
     Qh
    0.40
     pertenece
    0.39
     pertence
    0.39
    ="@+
    0.38
    (()=>{
    0.38
     pertenec
    0.37
     ခု
    0.37
    ActivityCompat
    0.36
     thánh
    0.36
    POSITIVE LOGITS
    s
    0.39
    Specific
    0.39
     This
    0.37
    ----------------
    0.37
    This
    0.37
     $[
    0.36
    Change
    0.35
    Replacing
    0.35
     😊
    0.35
    Identifying
    0.35
    Activations Density 0.009%

    No Known Activations