© 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. 11845
    Prev
    Next
    INDEX
    Explanations

    /topic/

    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
     bý
    0.38
    GraphQl
    0.37
    ਨੇ
    0.34
     plástico
    0.34
    放在
    0.33
    仳
    0.32
     piedi
    0.31
    隴
    0.31
     bisnis
    0.31
     edição
    0.31
    POSITIVE LOGITS
     storyboard
    0.44
    ards
    0.35
     Fawcett
    0.33
     match
    0.32
     Tug
    0.32
     anybody
    0.31
    ProgressBar
    0.31
     Curves
    0.31
    CLN
    0.31
     Yugoslav
    0.30
    Activations Density 0.001%

    No Known Activations