© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 204746
    Prev
    Next
    INDEX
    Explanations

    telegraph

    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
    𝟖
    0.44
    ﮩ
    0.38
    {{{
    0.38
     बृ
    0.38
    ★★
    0.37
     Buy
    0.36
     capas
    0.36
    _{(\
    0.36
     Architectural
    0.35
     Burke
    0.35
    POSITIVE LOGITS
    卟
    0.43
     predator
    0.39
    hesh
    0.39
    żu
    0.39
     polyclonal
    0.38
    我們可以
    0.38
    োর্ট
    0.38
     Residency
    0.38
     unstimulated
    0.38
    times
    0.37
    Activations Density 0.000%

    No Known Activations