© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134607
    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_1_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
     fenders
    0.96
    acing
    0.91
    ों
    0.90
    َ
    0.88
    ের
    0.86
    t
    0.84
     হাসপাত
    0.83
    ில்
    0.82
    ällt
    0.76
     attrakt
    0.76
    POSITIVE LOGITS
    2
    1.32
    of
    1.30
     was
    1.27
    1
    1.23
    for
    1.20
    は
    1.20
    는
    1.09
    시
    1.07
     for
    1.06
    SE
    1.05
    Activations Density 0.000%

    No Known Activations