© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88917
    Prev
    Next
    INDEX
    Explanations

    updated_at timestamp

    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_23_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
     કરવી
    0.43
    ृति
    0.41
    -"+
    0.41
    ..."
    0.39
    खी
    0.38
    UPS
    0.38
    тяну
    0.38
    ...),
    0.38
    gus
    0.37
    久し
    0.37
    POSITIVE LOGITS
     برابر
    0.44
    queous
    0.41
     odgovor
    0.41
     central
    0.40
     elemen
    0.40
     αυτο
    0.39
    _,
    0.39
     مرا
    0.38
     naz
    0.38
     engineer
    0.38
    Activations Density 0.000%

    No Known Activations