© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63740
    Prev
    Next
    INDEX
    Explanations

    hugging

    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_59_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
    face
    0.56
    Face
    0.56
    Faces
    0.55
     faces
    0.52
     face
    0.52
    脸上
    0.49
    FACE
    0.47
     F
    0.47
     Face
    0.46
    faces
    0.45
    POSITIVE LOGITS
    琲
    0.41
    vais
    0.40
     দেই
    0.40
    дав
    0.40
     kasih
    0.39
    avad
    0.38
    CEED
    0.38
     Enseñ
    0.38
     Sains
    0.37
    avas
    0.37
    Activations Density 0.001%

    No Known Activations