© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65896
    Prev
    Next
    INDEX
    Explanations

    range

    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
    AGO
    0.39
    ₲
    0.38
     trứng
    0.37
    hydroxyl
    0.37
    illante
    0.37
    lacian
    0.36
    عرِّف
    0.36
    τός
    0.35
     Paraná
    0.35
    createComponent
    0.35
    POSITIVE LOGITS
     Number
    0.47
    izate
    0.45
     Nine
    0.42
    %\
    0.41
     persen
    0.41
    %'
    0.40
     Twenty
    0.40
     Seven
    0.39
     ----->
    0.39
    Seven
    0.39
    Activations Density 0.005%

    No Known Activations