© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155876
    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_50_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
    ruciating
    0.38
    gruntled
    0.38
     Cen
    0.38
    ientos
    0.37
    áci
    0.37
    ếng
    0.37
    养
    0.37
    養
    0.37
     alg
    0.36
    Alg
    0.36
    POSITIVE LOGITS
    IPPING
    0.42
    𝙋
    0.42
    钏
    0.40
     chão
    0.40
    iesa
    0.39
     ভূপ
    0.39
    emie
    0.38
     Ria
    0.38
     saucer
    0.38
     RIC
    0.37
    Activations Density 0.000%

    No Known Activations