© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52641
    Prev
    Next
    INDEX
    Explanations

    melee attacks 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
     बाहरी
    0.39
    外出
    0.38
    汽车
    0.38
     settling
    0.37
    ινή
    0.36
     estren
    0.36
    𒇉
    0.36
    সা
    0.35
    营养
    0.35
    contenedor
    0.35
    POSITIVE LOGITS
     implication
    0.43
     knives
    0.42
     implicate
    0.40
     zooms
    0.39
     knife
    0.39
     Scrolls
    0.38
     close
    0.38
    क्ता
    0.38
     mno
    0.38
     implications
    0.37
    Activations Density 0.042%

    No Known Activations