© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217858
    Prev
    Next
    INDEX
    Explanations

    explosives and weapons

    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_31_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
     rifles
    0.38
    PointerException
    0.38
     firearms
    0.37
    นู
    0.36
    自
    0.35
     fors
    0.35
    兎
    0.35
    󠁴
    0.35
     klikken
    0.34
     Cali
    0.34
    POSITIVE LOGITS
    முத
    0.42
    auxite
    0.41
    omorphism
    0.40
     orth
    0.40
     passwd
    0.39
    IDS
    0.38
    ograph
    0.37
    antoms
    0.37
     சிற
    0.36
     আবশ্যক
    0.36
    Activations Density 0.025%

    No Known Activations