© 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. 215570
    Prev
    Next
    INDEX
    Explanations

    `.loc` 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_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
     I
    1.86
    ل
    1.63
    ك
    1.51
    .
    1.50
    ↵
    1.37
    م
    1.35
    การ
    1.30
    ت
    1.23
    ल
    1.20
    و
    1.20
    POSITIVE LOGITS
     to
    1.31
    0
    1.10
    𝟘
    1.08
    ۰
    1.04
    ௐ
    0.95
    மி
    0.93
    ља
    0.92
    ong
    0.92
    for
    0.92
    ０
    0.92
    Activations Density 0.001%

    No Known Activations