© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236908
    Prev
    Next
    INDEX
    Explanations

    Google

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Hym
    0.47
    Bab
    0.40
     휘
    0.38
    WORD
    0.37
     Aufmerksamkeit
    0.37
     vorticity
    0.36
     Afr
    0.36
     ஆயிர
    0.36
    ський
    0.36
    谄
    0.36
    POSITIVE LOGITS
    adi
    0.42
    alan
    0.40
    ears
    0.39
     baths
    0.38
    లం
    0.36
     مشتر
    0.36
    jars
    0.36
    发生
    0.35
    ලේ
    0.35
     ads
    0.35
    Activations Density 0.001%

    No Known Activations