© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102869
    Prev
    Next
    INDEX
    Explanations

    loop indices and array indexing

    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_16_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
     Dolores
    0.22
     adolescence
    0.20
     Ats
    0.20
    словия
    0.20
     molyb
    0.20
     Mizuno
    0.20
    攫
    0.20
    ampu
    0.20
    aceans
    0.19
     Acer
    0.19
    POSITIVE LOGITS
    ('
    0.23
    EN
    0.21
    Number
    0.20
    但是
    0.20
    H
    0.19
    G
    0.19
    但
    0.19
    大的
    0.19
    SIMPLE
    0.19
    ELE
    0.18
    Activations Density 0.028%

    No Known Activations