© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17330
    Prev
    Next
    INDEX
    Explanations

    Mission: Impossible, Harry Potter, fan fiction

    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_40_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
     Border
    0.38
     ፕሮ
    0.36
     Lac
    0.36
     border
    0.36
     scarcity
    0.35
     ENS
    0.35
    BORDER
    0.34
    鰍
    0.34
    jgl
    0.34
    sama
    0.34
    POSITIVE LOGITS
     synthesized
    0.39
     symbolized
    0.38
     synthetic
    0.36
    अर्
    0.36
     ninety
    0.36
     انته
    0.36
    outi
    0.36
    റെ
    0.35
    ética
    0.35
    Reviews
    0.35
    Activations Density 0.001%

    No Known Activations