© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258660
    Prev
    Next
    INDEX
    Explanations

    code blocks closing parenthesis followed by opening brace

    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_22_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
     identification
    0.54
     impor
    0.49
     antider
    0.49
     achie
    0.46
     antich
    0.45
    Identifying
    0.45
    ᆨ
    0.45
    Segue
    0.45
     helical
    0.44
     ultrasonic
    0.44
    POSITIVE LOGITS
     G
    0.44
     Nurse
    0.42
    ocarcinoma
    0.42
     pleinement
    0.42
    yss
    0.41
     পড়ে
    0.41
    все
    0.41
    awan
    0.40
     করিতেছি
    0.40
    ovu
    0.40
    Activations Density 0.000%

    No Known Activations