© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167574
    Prev
    Next
    INDEX
    Explanations

    one-third

    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_31_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
     अधीनस्थ
    0.45
    瀾
    0.40
     फेसबुक
    0.38
    interests
    0.37
     できる
    0.36
    剽
    0.36
     weaker
    0.35
     Interessen
    0.35
    /*'
    0.35
    constraints
    0.35
    POSITIVE LOGITS
     halt
    0.43
    akala
    0.41
     sleeper
    0.40
     soar
    0.39
     halde
    0.38
     gol
    0.37
     runner
    0.37
     runners
    0.37
    bauer
    0.37
     ENT
    0.37
    Activations Density 0.000%

    No Known Activations