© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200731
    Prev
    Next
    INDEX
    Explanations

    seasonal holidays and storage solution

    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_12_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
    É
    0.59
    Che
    0.56
    Ze
    0.55
    țit
    0.55
    V
    0.55
    RE
    0.54
    Pie
    0.54
    Tec
    0.54
     pelayanan
    0.54
    ֶ
    0.54
    POSITIVE LOGITS
     downloadable
    0.50
     HBO
    0.49
     Euclidean
    0.47
     donning
    0.47
     Algebra
    0.46
     Crusade
    0.46
     można
    0.45
     diab
    0.45
     marginBottom
    0.45
     Alphabet
    0.45
    Activations Density 0.001%

    No Known Activations