© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18258
    Prev
    Next
    INDEX
    Explanations

    elementary OS

    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_15_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
     टाइप्स
    0.49
    ۃ
    0.48
    esteem
    0.47
     তীর
    0.47
     personaggi
    0.47
    डील
    0.46
     hinder
    0.46
    vill
    0.46
     coin
    0.46
     minimo
    0.45
    POSITIVE LOGITS
    \"
    0.45
     Jefferson
    0.45
     Dang
    0.45
     Belanda
    0.43
     Jeddah
    0.42
    ;<
    0.41
    ुर
    0.41
     Yak
    0.41
    ;&#
    0.41
    \">
    0.41
    Activations Density 0.000%

    No Known Activations