© 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. 33470
    Prev
    Next
    INDEX
    Explanations

    C++ output

    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
     >>
    2.38
     <<
    2.33
    >>
    2.28
    <<
    2.14
     >>>
    1.80
    >>>
    1.73
    >>,
    1.72
    )<<
    1.72
     "<<
    1.66
    >>(
    1.64
    POSITIVE LOGITS
    ৤
    0.42
     munt
    0.37
    mtr
    0.36
     قالب
    0.36
    拦
    0.35
     Gale
    0.35
    𝑣
    0.35
     invariably
    0.34
     comis
    0.34
    ⋯
    0.34
    Activations Density 0.016%

    No Known Activations