© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36513
    Prev
    Next
    INDEX
    Explanations

    number of terms Fibonacci

    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_3_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
    fk
    0.82
    рсә
    0.80
    砚
    0.75
    fw
    0.72
     Canucks
    0.72
    كال
    0.71
     Karna
    0.71
    fte
    0.70
    ل
    0.70
    速度
    0.70
    POSITIVE LOGITS
    o
    1.30
    s
    0.96
    y
    0.92
    um
    0.85
     about
    0.83
     sobre
    0.83
    a
    0.80
    ه
    0.78
    ни
    0.76
    es
    0.75
    Activations Density 0.022%

    No Known Activations