© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62444
    Prev
    Next
    INDEX
    Explanations

    Mercantile, Mercruiser, Mercenary

    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_2_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
    ي
    1.92
    י
    1.60
    ه
    1.59
    us
    1.55
    x
    1.41
    ле
    1.41
    ر
    1.40
    те
    1.37
    으로
    1.34
    a
    1.34
    POSITIVE LOGITS
    ika
    1.06
    amis
    1.06
    ographic
    1.05
    annya
    1.05
    ick
    0.98
    izamos
    0.96
    rik
    0.95
    ong
    0.94
    ée
    0.93
    ale
    0.92
    Activations Density 0.000%

    No Known Activations