© 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. 86779
    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
     кількість
    0.75
    ER
    0.71
    äischen
    0.70
    ING
    0.68
     волосы
    0.67
     grasa
    0.67
    트
    0.64
     количества
    0.63
    一
    0.63
    ра
    0.63
    POSITIVE LOGITS
    !=
    0.61
    ]!=
    0.58
     stemmed
    0.55
    ceived
    0.53
    machen
    0.52
     decrypted
    0.52
    selves
    0.51
    торая
    0.50
    explore
    0.50
    savvy
    0.50
    Activations Density 0.000%

    No Known Activations