© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199404
    Prev
    Next
    INDEX
    Explanations

    decisions and focus

    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_46_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
     targ
    0.25
    ATOR
    0.25
     championed
    0.24
     parco
    0.23
     superbly
    0.23
    €¦
    0.22
    的重要性
    0.22
    व्यवस्था
    0.21
     dictated
    0.21
     πα
    0.21
    POSITIVE LOGITS
     Bayou
    0.28
    ō
    0.28
     Eck
    0.28
     mía
    0.26
     Mitchell
    0.25
     சிறிது
    0.25
     ҷ
    0.25
    يز
    0.25
     Karite
    0.24
     توهان
    0.24
    Activations Density 0.000%

    No Known Activations