© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14164
    Prev
    Next
    INDEX
    Explanations

    .to_string() or .to_dict() or .to_numpy()

    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_40_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
    Collapsed
    0.40
     riddled
    0.38
    गढ़
    0.37
    Quarter
    0.37
     독
    0.37
    jian
    0.36
    льність
    0.36
     pumped
    0.36
     gede
    0.36
     filer
    0.36
    POSITIVE LOGITS
    浪费
    0.38
     базо
    0.38
    હાસ
    0.35
     basi
    0.34
     โอเค
    0.34
     Ditto
    0.34
    attice
    0.34
    泓
    0.34
    writeFileSync
    0.34
     Dit
    0.34
    Activations Density 0.003%

    No Known Activations