© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93096
    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_60_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
    <i>
    0.59
     the
    0.55
     what
    0.55
     to
    0.55
    <em>
    0.52
     b
    0.52
     qu
    0.49
    <b>
    0.48
     so
    0.48
     say
    0.47
    POSITIVE LOGITS
    haben
    0.52
    HAS
    0.51
    RESH
    0.50
     তাদের
    0.45
    Their
    0.45
    他们的
    0.44
    Liked
    0.44
    avanje
    0.43
    ächst
    0.42
    fehlung
    0.41
    Activations Density 0.000%

    No Known Activations