© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32853
    Prev
    Next
    INDEX
    Explanations

    numbers and arithmetic operations

    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
     Faust
    0.30
    flask
    0.30
    Flask
    0.29
    驿
    0.29
     recoil
    0.29
    ယ
    0.29
    தமி
    0.28
    éndose
    0.28
    शिष्ट
    0.28
     ယ
    0.28
    POSITIVE LOGITS
     initializes
    0.33
     Lover
    0.32
     sockaddr
    0.32
    꿨
    0.30
     Schritt
    0.29
     मासिक
    0.29
     ספר
    0.29
     subtracted
    0.29
     Lovers
    0.29
    لر
    0.28
    Activations Density 0.005%

    No Known Activations