© 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. 17726
    Prev
    Next
    INDEX
    Explanations

    text and images input

    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
    hape
    0.41
    álie
    0.41
     fathers
    0.39
    textepsilon
    0.38
     അവളുടെ
    0.36
    ┐
    0.35
    └
    0.35
     spal
    0.34
     জানানো
    0.33
    zetten
    0.33
    POSITIVE LOGITS
    ্যাড
    0.40
     exodus
    0.39
    OCO
    0.39
     сов
    0.37
    utip
    0.37
    exit
    0.37
    Vk
    0.36
    Uri
    0.36
    Ξ
    0.36
    boom
    0.36
    Activations Density 0.016%

    No Known Activations