© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9650
    Prev
    Next
    INDEX
    Explanations

    chemical formulas

    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
     wf
    0.41
     Replacement
    0.40
     wx
    0.40
    有的
    0.38
    ordinal
    0.37
    쌈
    0.37
    Pars
    0.36
     estructura
    0.36
    attlist
    0.35
    деги
    0.35
    POSITIVE LOGITS
     Symmetry
    0.44
    पीजी
    0.38
    symmetry
    0.38
     전에
    0.38
     Saar
    0.37
    uhu
    0.37
    腸
    0.37
     РАН
    0.36
    ionante
    0.35
     कोश
    0.35
    Activations Density 0.054%

    No Known Activations