© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158774
    Prev
    Next
    INDEX
    Explanations

    heat

    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_50_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
    tencent
    0.38
    Ĵ
    0.38
    textarea
    0.37
     ଚ
    0.37
    㧍
    0.37
     textarea
    0.37
     megs
    0.37
    <0x9A>
    0.36
    <unused491>
    0.36
     answer
    0.35
    POSITIVE LOGITS
     L
    0.39
    மன்
    0.39
     ল
    0.38
    μφωνα
    0.38
     루
    0.37
     ersch
    0.37
    𝗯
    0.37
    Ⅼ
    0.37
    মধ
    0.37
     جات
    0.37
    Activations Density 0.000%

    No Known Activations