© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179174
    Prev
    Next
    INDEX
    Explanations

    weapon and defense

    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_29_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
     ettevõ
    0.42
     različ
    0.40
     Valt
    0.39
     شركة
    0.38
    匏
    0.38
     Settlement
    0.38
    recation
    0.38
     खिल
    0.38
     acuerdo
    0.38
    uthi
    0.38
    POSITIVE LOGITS
    denominator
    0.41
     denominators
    0.40
     একটা
    0.39
     denominator
    0.38
     έναν
    0.38
     backbone
    0.37
    英語版
    0.37
     একজন
    0.37
    ύ
    0.37
     antit
    0.36
    Activations Density 0.007%

    No Known Activations