© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161463
    Prev
    Next
    INDEX
    Explanations

    WSL (Windows Subsystem for Linux)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    م
    1.64
    ش
    1.58
    ج
    1.48
    يل
    1.46
    ين
    1.44
    وم
    1.33
    на
    1.27
    ى
    1.27
    ک
    1.23
    αν
    1.20
    POSITIVE LOGITS
    ,
    1.58
    /
    1.21
    1.06
     is
    0.98
    -
    0.97
     Professionals
    0.91
    iD
    0.90
    ;
    0.90
    )]
    0.87
    i
    0.84
    Activations Density 0.000%

    No Known Activations