© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197887
    Prev
    Next
    INDEX
    Explanations

    ABAP code report

    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
    itol
    0.40
     پائی
    0.39
    乙
    0.38
    anci
    0.38
     आएंगी
    0.38
    ilog
    0.38
     शि
    0.37
     hyperplasia
    0.37
     आएगी
    0.37
     Nauk
    0.36
    POSITIVE LOGITS
     ღ
    0.40
     daemon
    0.38
     repub
    0.38
    Prepar
    0.38
     debris
    0.37
     Prepar
    0.37
    exe
    0.36
     леп
    0.36
     smith
    0.36
    ッカー
    0.36
    Activations Density 0.001%

    No Known Activations