© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 181638
    Prev
    Next
    INDEX
    Explanations

    illegal and dangerous manufacturing

    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
    ާމ
    0.41
     typically
    0.40
    Compart
    0.38
     umożliw
    0.38
     hat
    0.38
    Hat
    0.36
    ____________
    0.36
    Montgomery
    0.36
    മതി
    0.35
     justifyContent
    0.35
    POSITIVE LOGITS
     име
    0.42
     Shift
    0.41
     shift
    0.40
    诽
    0.39
    SHIFT
    0.39
    shift
    0.38
    shifted
    0.38
    şı
    0.36
     பெற்றோ
    0.36
    眼的
    0.36
    Activations Density 0.015%

    No Known Activations