© 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. 205813
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    atak
    0.42
    atian
    0.40
     പ്രാ
    0.37
     সাম্প্র
    0.36
    gevens
    0.36
    eber
    0.35
    厂
    0.35
    atah
    0.35
    偲
    0.35
     сиг
    0.34
    POSITIVE LOGITS
     DN
    0.42
     Apollo
    0.41
     SES
    0.40
     Benito
    0.40
     Moch
    0.40
     cold
    0.39
     Hoop
    0.38
     Cold
    0.37
     হচ্ছিল
    0.37
     موس
    0.36
    Activations Density 0.003%

    No Known Activations