© 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. 59059
    Prev
    Next
    INDEX
    Explanations

    formal

    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
    m
    1.78
    '
    1.65
    เป็น
    1.42
    p
    1.16
    ’
    1.09
    z
    1.08
    。
    1.05
    '>
    1.04
    og
    1.03
     och
    1.03
    POSITIVE LOGITS
    ح
    1.26
    ח
    1.23
     and
    1.20
    д
    1.20
    дят
    1.15
    ک
    1.15
    ために
    1.12
    ال
    1.09
    сё
    1.08
    ደት
    1.08
    Activations Density 0.001%

    No Known Activations