© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134647
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript configuration

    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_37_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
     orientation
    0.46
     orientations
    0.43
     flip
    0.43
     Flip
    0.41
     cover
    0.40
     புத்தக
    0.40
    älter
    0.39
    扈
    0.39
     UT
    0.38
     cited
    0.37
    POSITIVE LOGITS
     Cá
    0.43
    Cris
    0.40
    调
    0.40
    Tier
    0.37
    வனே
    0.37
    調
    0.36
     Olson
    0.35
    㗊
    0.34
    Chicken
    0.34
    Cox
    0.34
    Activations Density 0.004%

    No Known Activations