© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 119753
    Prev
    Next
    INDEX
    Explanations

    Git, ML, text formatting

    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_27_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
     Mode
    0.40
     করপোর
    0.39
     Productivity
    0.39
     ১০০
    0.38
     integrations
    0.38
     Variant
    0.37
     '=
    0.37
    planade
    0.37
     productivity
    0.37
     vitro
    0.37
    POSITIVE LOGITS
    த்தே
    0.37
    owanym
    0.35
    たん
    0.35
    核
    0.34
    ット
    0.34
     ሁሉ
    0.33
    因为它
    0.32
    ছিল
    0.32
     eh
    0.32
     тъ
    0.32
    Activations Density 0.016%

    No Known Activations