© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27303
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    r
    0.53
    am
    0.52
    all
    0.50
    c
    0.49
    an
    0.49
    em
    0.47
     life
    0.47
    produced
    0.46
    deadline
    0.45
     salinity
    0.44
    POSITIVE LOGITS
     idxf
    0.58
    ট্র
    0.57
    탄소년단
    0.53
    জ
    0.51
     pueblos
    0.51
    thal
    0.49
    𝗸
    0.49
    オブジェクト
    0.49
    ლი
    0.49
    кти
    0.48
    Activations Density 0.000%

    No Known Activations