© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5342
    Prev
    Next
    INDEX
    Explanations

    skeptical doubt

    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_39_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
    itemconfig
    0.36
     datt
    0.32
    refrac
    0.31
    ⾏
    0.31
     indem
    0.31
    ละ
    0.30
    запа
    0.30
    irdik
    0.30
    अला
    0.29
     transgenic
    0.29
    POSITIVE LOGITS
     डाउट
    0.35
     Jug
    0.34
     ved
    0.33
    जिया
    0.32
    
    0.32
     pers
    0.32
     Calm
    0.32
     Pers
    0.31
     skept
    0.31
     Seek
    0.31
    Activations Density 0.237%

    No Known Activations