© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138130
    Prev
    Next
    INDEX
    Explanations

    coordinates and calculations

    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
    差
    0.51
    差异
    0.45
     difer
    0.45
     différence
    0.43
     róż
    0.41
    差距
    0.41
     diferencia
    0.41
     maksimum
    0.40
    bigvee
    0.39
     kreatif
    0.39
    POSITIVE LOGITS
     (,
    0.41
     연락
    0.37
     underworld
    0.37
    (:,
    0.36
    ({'
    0.36
    、「
    0.36
    (.
    0.36
    ($
    0.35
     Exchange
    0.35
     Profits
    0.35
    Activations Density 0.005%

    No Known Activations