© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18130
    Prev
    Next
    INDEX
    Explanations

    module probe loading

    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_15_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
    e
    0.22
    l
    0.22
    ;
    0.21
    s
    0.21
    )
    0.19
    f
    0.19
    >
    0.19
     –
    0.19
    atti
    0.19
    ك
    0.18
    POSITIVE LOGITS
     包
    0.21
    
    0.20
    كلمنا
    0.19
     preorder
    0.19
     കത്തി
    0.19
    ylmethylsulfanyl
    0.19
     Größe
    0.19
    größe
    0.19
     Funktion
    0.19
    rbrakk
    0.19
    Activations Density 0.007%

    No Known Activations