© 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. 92714
    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
     Un
    0.54
    Un
    0.45
    の写真
    0.42
     Pics
    0.42
    を下
    0.40
    wider
    0.39
    、
    0.37
     Keys
    0.36
    াদার
    0.36
    へと
    0.36
    POSITIVE LOGITS
     disclosure
    0.63
     disclose
    0.61
    Disclosure
    0.58
     disclosed
    0.55
     (
    0.54
     wak
    0.53
    ”,
    0.53
     disclosing
    0.53
    <i>
    0.52
     »,
    0.51
    Activations Density 0.000%

    No Known Activations