© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102918
    Prev
    Next
    INDEX
    Explanations

    Rust println

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     diffusive
    0.43
     वॉल
    0.43
     జరిగిన
    0.42
     بالغ
    0.40
     Bước
    0.39
     melakukan
    0.39
     सीनियर
    0.39
     |_{
    0.38
     nuôi
    0.38
    護
    0.38
    POSITIVE LOGITS
    AC
    0.43
    Car
    0.42
    Cardinal
    0.38
    Card
    0.38
    Eric
    0.38
    aced
    0.38
    Wil
    0.38
    เป
    0.37
    Marcel
    0.36
     Calvert
    0.36
    Activations Density 0.002%

    No Known Activations