© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39999
    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_57_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
     "/")
    0.38
    ("/"))
    0.38
    一面
    0.37
     जानेंगे
    0.37
     পছন্দের
    0.36
     جارہ
    0.36
    悆
    0.36
     ஒருவர்
    0.36
    াসন
    0.36
    簋
    0.36
    POSITIVE LOGITS
    Fi
    0.42
    aments
    0.42
    fé
    0.41
    ames
    0.41
    Ls
    0.41
    nelles
    0.40
    ograft
    0.39
    Pi
    0.39
    emies
    0.38
    っていた
    0.38
    Activations Density 0.000%

    No Known Activations