© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142296
    Prev
    Next
    INDEX
    Explanations

    cryptocurrencies and cryptography

    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_0_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
    a
    1.92
    ה
    1.80
    st
    1.70
    ه
    1.62
    تی
    1.61
    us
    1.60
    یات
    1.42
    at
    1.36
    f
    1.34
    and
    1.33
    POSITIVE LOGITS
    2.22
     instala
    1.46
     is
    1.38
    是
    1.38
     are
    1.37
     verzi
    1.30
     produz
    1.22
     conversaciones
    1.20
     kayaks
    1.20
    ü
    1.20
    Activations Density 0.002%

    No Known Activations