© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178957
    Prev
    Next
    INDEX
    Explanations

    say "blood"

    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_50_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
    ρες
    0.40
    噘
    0.39
    isał
    0.36
    ρας
    0.35
    timeout
    0.35
     FIFO
    0.35
    τια
    0.34
    nameSort
    0.34
    ཋ
    0.34
     Syntax
    0.34
    POSITIVE LOGITS
     blood
    3.69
    Blood
    3.48
     Blood
    3.39
    blood
    3.34
    血
    3.28
     BLOOD
    3.19
     रक्त
    2.91
    血液
    2.91
     sangue
    2.88
     خون
    2.88
    Activations Density 0.009%

    No Known Activations