© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14746
    Prev
    Next
    INDEX
    Explanations

    claim and associated words

    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_15_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
    熙
    0.54
    批
    0.50
     ethylene
    0.50
     pipelines
    0.50
     scrapes
    0.48
    享
    0.48
     keeping
    0.47
    ناة
    0.46
     pacing
    0.46
     base
    0.46
    POSITIVE LOGITS
    w
    0.71
    il
    0.63
    st
    0.62
    St
    0.61
    a
    0.60
    aS
    0.59
    Ig
    0.59
     Ос
    0.58
    </h2>
    0.56
    ver
    0.56
    Activations Density 0.003%

    No Known Activations