© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120114
    Prev
    Next
    INDEX
    Explanations

    describing static or sensory details

    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_27_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
     Skins
    0.38
     reapp
    0.37
    ുകള്‍
    0.36
    SRPC
    0.36
     डेस्क
    0.36
    стру
    0.35
    OG
    0.35
    폼
    0.35
     runApp
    0.35
    녹
    0.34
    POSITIVE LOGITS
     interruption
    0.38
     deception
    0.37
     لە
    0.37
    企業の
    0.37
     pendant
    0.37
     យើង
    0.36
    曩
    0.36
    раль
    0.35
     gaze
    0.35
     iri
    0.35
    Activations Density 0.024%

    No Known Activations