© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216244
    Prev
    Next
    INDEX
    Explanations

    continuing, continuation

    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
     hij
    0.37
     shod
    0.36
    ंबे
    0.36
     obiect
    0.36
     lustre
    0.35
    satellite
    0.35
    assisted
    0.34
    姗
    0.34
    because
    0.34
    guided
    0.34
    POSITIVE LOGITS
     පිළ
    0.42
    ทัน
    0.40
    礡
    0.37
     कपकेक
    0.37
    ophora
    0.36
    aterData
    0.35
    数据显示
    0.35
     மெ
    0.35
     മെ
    0.35
     мг
    0.34
    Activations Density 0.001%

    No Known Activations