© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134262
    Prev
    Next
    INDEX
    Explanations

    har

    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_37_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
     motocicleta
    0.41
    нора
    0.40
     diligent
    0.39
    .|__
    0.38
     due
    0.37
     Stre
    0.37
     মোত
    0.37
     vigilant
    0.36
    moc
    0.36
     medio
    0.36
    POSITIVE LOGITS
     лицен
    0.42
     ವ
    0.37
    くだ
    0.36
    מבר
    0.36
    illusion
    0.35
    getBounding
    0.35
    埋
    0.35
    텀
    0.35
    ер
    0.35
    কল্যা
    0.35
    Activations Density 0.002%

    No Known Activations