© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    Statutes of Artificers

    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
    batross
    0.38
    駕
    0.38
     വെള്ള
    0.37
    τσ
    0.36
    Analyzing
    0.36
    ண்மை
    0.36
    vergne
    0.35
     differentiate
    0.35
    坟
    0.35
    
    0.35
    POSITIVE LOGITS
     ren
    0.41
    кция
    0.40
     <<<
    0.38
    өр
    0.37
     Ren
    0.36
    REN
    0.36
     objString
    0.36
    가는
    0.36
    renal
    0.35
     REN
    0.35
    Activations Density 0.012%

    No Known Activations