© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210252
    Prev
    Next
    INDEX
    Explanations

    special characters and quotes

    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_5_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
    data
    1.26
    designed
    1.18
    “
    1.18
    ות
    1.13
    a
    1.13
    don
    1.12
     synthes
    1.12
    at
    1.10
    н
    1.10
    dist
    1.06
    POSITIVE LOGITS
    م
    1.29
    مش
    1.23
    <0x0D>
    1.14
    ক
    1.07
    ip
    1.05
    מ
    1.04
     préférable
    1.02
    مي
    1.02
    ا
    1.02
     rápido
    0.99
    Activations Density 0.000%

    No Known Activations