© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137789
    Prev
    Next
    INDEX
    Explanations

    It

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    abilité
    0.40
     Matters
    0.38
     ставки
    0.38
     słu
    0.37
    UNRELATED
    0.37
     matters
    0.35
     겁
    0.35
    द्वीप
    0.35
    枓
    0.34
    Sd
    0.34
    POSITIVE LOGITS
     read
    1.37
    read
    1.27
     Read
    1.11
     reads
    1.08
    Read
    1.05
    อ่าน
    1.00
     đọc
    0.97
     READ
    0.97
     읽
    0.96
    读
    0.95
    Activations Density 0.006%

    No Known Activations