© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75213
    Prev
    Next
    INDEX
    Explanations

    book or film titles

    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_31_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
     PHOTO
    0.36
    ホ
    0.36
     ಚುನಾವಣ
    0.35
    写真
    0.34
    ᴋ
    0.34
    鑑定
    0.34
     computation
    0.33
    ృష్టి
    0.33
    图片的
    0.33
     diminuer
    0.33
    POSITIVE LOGITS
    рама
    0.39
    tiin
    0.38
     rama
    0.38
    atkan
    0.37
    aham
    0.37
    avalt
    0.36
     dz
    0.36
    <unused98>
    0.36
     Rama
    0.35
    ramas
    0.35
    Activations Density 0.007%

    No Known Activations