© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122084
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
     to
    1.16
     framed
    0.79
    se
    0.78
    A
    0.77
    幀
    0.76
    帧
    0.73
    Frame
    0.73
     frames
    0.73
    Y
    0.73
     be
    0.72
    POSITIVE LOGITS
    彷
    0.73
    ał
    0.68
    는
    0.66
    ्वती
    0.57
    ammlung
    0.56
     टीच
    0.55
    టీఎం
    0.55
    蜞
    0.55
     IMPLIED
    0.54
    芢
    0.54
    Activations Density 0.000%

    No Known Activations