© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258839
    Prev
    Next
    INDEX
    Explanations

    knowledge cutoff is limited

    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_22_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
     Parts
    0.38
    ቢ
    0.38
    onzo
    0.37
    onces
    0.37
    oxidase
    0.37
    bridge
    0.36
     biore
    0.36
     ஆணைய
    0.36
     গে
    0.36
    വശ
    0.35
    POSITIVE LOGITS
     getDateTime
    0.39
     scarred
    0.38
     risus
    0.36
    UNITED
    0.36
     resembled
    0.35
    拠
    0.35
     resembles
    0.35
     siitä
    0.35
    馏
    0.35
    럼
    0.35
    Activations Density 0.004%

    No Known Activations