© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102793
    Prev
    Next
    INDEX
    Explanations

    container for

    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_16_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
    🕎
    0.56
     Himachal
    0.52
    ニング
    0.51
     Maharashtra
    0.50
    青森
    0.50
    响起
    0.50
     সেপ্টেম্বর
    0.49
     Namibia
    0.49
    ിത്ര
    0.49
     कलर
    0.47
    POSITIVE LOGITS
    à
    0.63
    gie
    0.59
    avoir
    0.59
    cer
    0.58
    entre
    0.58
    ains
    0.57
    alty
    0.57
    ads
    0.57
    ate
    0.56
    ceria
    0.55
    Activations Density 0.004%

    No Known Activations