© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82110
    Prev
    Next
    INDEX
    Explanations

    urges

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     cont
    0.38
    ட்
    0.37
    cont
    0.36
    IONAL
    0.36
     CONT
    0.35
     tangent
    0.35
     pari
    0.34
     ;,
    0.34
     knock
    0.34
     diligently
    0.33
    POSITIVE LOGITS
    æs
    0.39
    omas
    0.38
    ucci
    0.38
    अस
    0.37
    ផ្ស
    0.36
    Ма
    0.35
    ————————————————
    0.35
    joe
    0.35
     resuming
    0.35
     Crawford
    0.34
    Activations Density 0.003%

    No Known Activations