© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68356
    Prev
    Next
    INDEX
    Explanations

    jolly bearded man

    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_46_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
    βο
    0.44
     Mandal
    0.43
     M
    0.42
    archiv
    0.39
     EDU
    0.38
     EDUCATION
    0.38
    ushu
    0.38
     ترم
    0.37
     Mor
    0.36
    犸
    0.36
    POSITIVE LOGITS
     fat
    0.67
     fatty
    0.64
     Jolly
    0.57
     jolly
    0.55
     fatt
    0.54
     bearded
    0.54
     FAT
    0.51
     Fatt
    0.51
    脂肪
    0.50
    fat
    0.50
    Activations Density 0.022%

    No Known Activations