© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14639
    Prev
    Next
    INDEX
    Explanations

    watch or security-related terms

    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_40_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
     گروپ
    0.40
    DET
    0.39
    IFS
    0.39
    Group
    0.38
     sugger
    0.38
    洞
    0.38
     Hosted
    0.38
    堌
    0.37
    ಶಿ
    0.37
    ِيم
    0.37
    POSITIVE LOGITS
     ڪري
    0.44
    Overflow
    0.42
    Hochspringen
    0.39
     Overflow
    0.37
     ctypes
    0.36
     콘텐츠
    0.36
    lications
    0.35
    iseconds
    0.34
     cerebrospinal
    0.34
     списка
    0.34
    Activations Density 0.046%

    No Known Activations