© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53396
    Prev
    Next
    INDEX
    Explanations

    core: dependencies, versions, or components

    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_31_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
     core
    0.39
    
    0.39
     لال
    0.38
    hesians
    0.37
     Ely
    0.37
     belladone
    0.36
    ≣
    0.36
     corret
    0.36
     caballos
    0.36
     nahm
    0.35
    POSITIVE LOGITS
    环节
    0.39
    Support
    0.37
     рецеп
    0.37
    胀
    0.37
    न्ति
    0.36
     Claus
    0.36
    consc
    0.36
    River
    0.35
    थि
    0.35
    adaan
    0.35
    Activations Density 0.001%

    No Known Activations