© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195774
    Prev
    Next
    INDEX
    Explanations

    document databases

    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_4_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
    es
    1.00
    editing
    0.82
    h
    0.80
    eff
    0.77
    rope
    0.77
    i
    0.76
    ence
    0.75
    ep
    0.75
    ee
    0.74
    u
    0.71
    POSITIVE LOGITS
    ن
    1.06
    ק
    1.02
    น
    0.98
    প
    0.96
    ν
    0.86
    که
    0.86
    ן
    0.84
    ก
    0.81
    ک
    0.80
     for
    0.80
    Activations Density 0.001%

    No Known Activations