© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183551
    Prev
    Next
    INDEX
    Explanations

    then or afterwards

    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_29_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
     সত
    0.38
    .)
    0.37
     Pic
    0.36
     XO
    0.35
     DeFi
    0.35
     Baum
    0.34
     Paese
    0.34
    )%
    0.34
     giảm
    0.34
     ایک
    0.33
    POSITIVE LOGITS
     затем
    0.44
     następnie
    0.43
     kemudian
    0.40
     luego
    0.39
    ຖານ
    0.38
    నీ
    0.37
    ąc
    0.37
     месяц
    0.37
     później
    0.36
     سپس
    0.36
    Activations Density 0.031%

    No Known Activations