© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 194029
    Prev
    Next
    INDEX
    Explanations

    numbers and math

    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_27_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
    instance
    0.41
    chequer
    0.38
    ờ
    0.36
     에게
    0.35
     năng
    0.35
    iver
    0.34
    dings
    0.34
    чик
    0.34
     \[
    0.34
    instances
    0.34
    POSITIVE LOGITS
     задержа
    0.38
     pozosta
    0.37
    TintMode
    0.36
    筅
    0.36
     drawRight
    0.35
    老師
    0.35
    袮
    0.35
    社長
    0.34
    צור
    0.34
     یار
    0.34
    Activations Density 0.000%

    No Known Activations