© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81095
    Prev
    Next
    INDEX
    Explanations

    lending money

    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
     to
    1.93
    to
    1.89
     be
    1.67
    ;
    1.53
    </h3>
    1.45
    هم
    1.34
    را
    1.33
    ৮
    1.32
    きた
    1.28
     политика
    1.27
    POSITIVE LOGITS
    an
    2.05
    et
    1.46
    elle
    1.37
    ed
    1.27
    н
    1.23
    on
    1.22
    न
    1.20
    att
    1.15
    lar
    1.14
    ه
    1.09
    Activations Density 0.000%

    No Known Activations