© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123775
    Prev
    Next
    INDEX
    Explanations

    Azure Blob Storage

    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_3_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
    í
    0.88
    л
    0.84
    й
    0.76
    ร
    0.72
    ร้าย
    0.66
     t
    0.65
    य
    0.62
     l
    0.62
    u
    0.62
    ل
    0.62
    POSITIVE LOGITS
    tens
    0.74
    tuning
    0.72
    とっても
    0.70
    aid
    0.68
    σια
    0.68
    dach
    0.67
    bamos
    0.66
    lytres
    0.66
    traumatic
    0.66
    tanggal
    0.66
    Activations Density 0.001%

    No Known Activations