© 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. 107356
    Prev
    Next
    INDEX
    Explanations

    midterm exam elections study term

    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
    1.00
    GUI
    0.93
    }
    0.92
    ↵
    0.89
    )
    0.84
    }{
    0.82
    ER
    0.82
    ู
    0.80
    ﻼ
    0.80
    IS
    0.79
    POSITIVE LOGITS
    an
    1.54
    as
    1.43
    ма
    1.42
    ن
    1.38
    س
    1.34
    ס
    1.33
    on
    1.32
    ان
    1.23
     are
    1.19
    ני
    1.18
    Activations Density 0.001%

    No Known Activations