© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246507
    Prev
    Next
    INDEX
    Explanations

    focused on

    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_40_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
    يكا
    0.42
     Appliance
    0.38
     अधिसू
    0.38
     reposition
    0.37
    ун
    0.37
    楾
    0.36
    auti
    0.36
     tvam
    0.36
    ત
    0.36
    piel
    0.36
    POSITIVE LOGITS
     Built
    0.41
     Build
    0.41
     execution
    0.40
     Builds
    0.39
    受到了
    0.39
    Build
    0.39
     Execution
    0.38
    Built
    0.38
     build
    0.37
     builds
    0.37
    Activations Density 0.012%

    No Known Activations