© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 82541
    Prev
    Next
    INDEX
    Explanations

    lists of strings

    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_29_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
     template
    0.37
     determination
    0.37
    determination
    0.36
    を変更
    0.35
    狷
    0.35
     κ
    0.35
    ického
    0.34
     ս
    0.34
     \|
    0.34
     potion
    0.34
    POSITIVE LOGITS
    Các
    0.43
     تعدد
    0.42
     packets
    0.41
     múlt
    0.40
     Các
    0.40
    irst
    0.39
     criss
    0.39
    oles
    0.39
    cycles
    0.38
    groupby
    0.38
    Activations Density 0.020%

    No Known Activations