© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51803
    Prev
    Next
    INDEX
    Explanations

    User, responsible, install, learning

    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_31_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
     ғ
    0.31
    RIM
    0.30
    OutputType
    0.29
    转载
    0.29
     தொட
    0.28
    REE
    0.28
    вра
    0.28
    CMAKE
    0.28
    បរ
    0.28
    続ける
    0.27
    POSITIVE LOGITS
     لكن
    0.34
     But
    0.33
    ago
    0.31
    altung
    0.31
     News
    0.30
    曦
    0.30
    angelo
    0.29
     ladder
    0.29
    %%
    0.29
    ⑪
    0.28
    Activations Density 0.009%

    No Known Activations