© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31643
    Prev
    Next
    INDEX
    Explanations

    chemical components and materials

    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
    imbangan
    0.40
    cars
    0.40
    頻
    0.39
    情報を
    0.38
    zeg
    0.38
    zana
    0.38
    tugraz
    0.38
    strahlung
    0.38
    gna
    0.38
    bardziej
    0.37
    POSITIVE LOGITS
     norepinephrine
    0.43
     trivalent
    0.39
     ढाई
    0.39
     `$
    0.38
    спекти
    0.37
     Peabody
    0.37
    michael
    0.37
     Schwe
    0.36
     Co
    0.36
     Ender
    0.36
    Activations Density 0.001%

    No Known Activations