© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214061
    Prev
    Next
    INDEX
    Explanations

    Rather

    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
     jährlich
    0.39
     ដោយ
    0.39
    揚げ
    0.39
    をご
    0.39
    ದಲ
    0.38
    挙げ
    0.37
     verwendet
    0.37
    Ỡ
    0.37
    offel
    0.37
    äng
    0.36
    POSITIVE LOGITS
     brengen
    0.49
     bring
    0.45
    Kal
    0.43
     bringing
    0.43
    Bringing
    0.43
    化
    0.43
     Bring
    0.42
    Bring
    0.42
    bringing
    0.40
     Kal
    0.39
    Activations Density 0.003%

    No Known Activations