© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58824
    Prev
    Next
    INDEX
    Explanations

    ib followed by common internet/code terms

    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_2_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
    ма
    1.41
    های
    1.22
    ната
    1.17
    ї
    1.16
     are
    1.15
    ä
    1.13
    ır
    1.09
    ку
    1.08
    که
    1.06
    کس
    1.04
    POSITIVE LOGITS
    B
    1.34
    J
    1.09
    K
    1.06
    Z
    1.02
    使用
    0.99
    போது
    0.98
    ↵↵
    0.94
    D
    0.93
    新
    0.93
     ochron
    0.89
    Activations Density 0.001%

    No Known Activations