© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97655
    Prev
    Next
    INDEX
    Explanations

    defense walls

    np_acts-logits-general · gemini-2.5-flash-lite

    walls defense infrastructure

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi

    technical terms related to distributed storage systems and words used in language learning explanations.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_14_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
    Kh
    0.15
     propriedades
    0.13
    
    0.13
     HPE
    0.12
    ंचित
    0.12
    UM
    0.12
     G
    0.12
     Helium
    0.12
    óis
    0.12
    Helix
    0.12
    POSITIVE LOGITS
    d
    0.14
    くちゃ
    0.13
    న్
    0.12
    らの
    0.12
    رويج
    0.12
    唛
    0.12
     perder
    0.11
     ಆಹಾರ
    0.11
     aquatic
    0.11
    气的
    0.11
    Activations Density 0.003%

    No Known Activations