© 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. 166737
    Prev
    Next
    INDEX
    Explanations

    "So it"

    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
     causado
    0.38
     managable
    0.38
    ঐ
    0.35
     ለመ
    0.35
    lüğ
    0.35
    unprocessable
    0.35
    ซึ่ง
    0.35
     franca
    0.35
     Faye
    0.34
     fluke
    0.34
    POSITIVE LOGITS
     Unlike
    0.52
    Unlike
    0.49
     Instead
    0.42
    SOFTWARE
    0.41
    "-"
    0.37
     সফট
    0.37
    Software
    0.37
    ソフトウェア
    0.37
    INDIC
    0.37
    Instead
    0.36
    Activations Density 0.003%

    No Known Activations