© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169995
    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_56_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
    –
    0.46
     durable
    0.45
     Dé
    0.44
    -\\
    0.44
    -'
    0.43
    ÁN
    0.42
    ám
    0.42
    Dé
    0.41
     -
    0.41
    -\
    0.40
    POSITIVE LOGITS
     ere
    0.41
    畀
    0.40
    വാ
    0.40
    acariy
    0.40
     ву
    0.38
    中毒
    0.38
    θεση
    0.38
    振動
    0.37
    bere
    0.37
    ဤ
    0.37
    Activations Density 0.000%

    No Known Activations