© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211825
    Prev
    Next
    INDEX
    Explanations

    fees

    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_43_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
    each
    0.45
    itous
    0.44
     each
    0.38
    ونات
    0.38
     charges
    0.37
    accharides
    0.37
    iella
    0.37
     /\.
    0.36
    charges
    0.36
     charge
    0.36
    POSITIVE LOGITS
     kurs
    0.44
    fassung
    0.44
    গতির
    0.41
     wafer
    0.41
     EO
    0.41
     VAT
    0.40
     issued
    0.40
     Kurs
    0.39
     Whisky
    0.39
    ாந்து
    0.39
    Activations Density 0.003%

    No Known Activations