© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129617
    Prev
    Next
    INDEX
    Explanations

    Plumbago, Game, Urvillea, isms, NMR, Shades

    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_25_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
    皞
    0.38
     agak
    0.37
     protección
    0.37
     thisobject
    0.37
    Radiux
    0.37
    సారి
    0.36
     ordenada
    0.36
    myItem
    0.36
    𝚏
    0.36
    waża
    0.35
    POSITIVE LOGITS
    CN
    0.35
     P
    0.34
     S
    0.34
     sizzling
    0.33
    ोटी
    0.33
     बनी
    0.33
    奔
    0.32
     oppure
    0.32
    Cell
    0.32
    BN
    0.32
    Activations Density 0.016%

    No Known Activations