© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198296
    Prev
    Next
    INDEX
    Explanations

    sequences and order

    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
     appart
    0.39
     equival
    0.36
    擀
    0.35
    ₁(
    0.34
     suppose
    0.34
    appart
    0.34
     раздел
    0.33
    }):=\
    0.33
    那我們
    0.33
    導數
    0.33
    POSITIVE LOGITS
     pretty
    0.37
     victoria
    0.36
     NBS
    0.36
    Az
    0.35
     HU
    0.34
     Sly
    0.34
    HU
    0.33
    Sh
    0.33
    rho
    0.33
     mengikuti
    0.33
    Activations Density 0.001%

    No Known Activations