© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29034
    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_10_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
     J
    0.49
    ing
    0.47
     p
    0.46
    rote
    0.45
    ales
    0.44
    —
    0.44
    )$
    0.43
     specialized
    0.43
    onia
    0.42
     structurally
    0.42
    POSITIVE LOGITS
     appellees
    0.61
    ের
    0.54
    зму
    0.54
    ༎
    0.53
    ી
    0.53
    呕
    0.53
    鲅
    0.52
     छु
    0.52
     Automobiles
    0.51
    嫔
    0.51
    Activations Density 0.000%

    No Known Activations