© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89232
    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_23_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
     VOLUME
    0.47
     ريا
    0.46
    Atm
    0.43
     Scheduling
    0.42
    スケジュール
    0.42
     இயற்கை
    0.41
    肋
    0.40
     ২০২০
    0.40
     첨
    0.39
     진
    0.39
    POSITIVE LOGITS
     begr
    0.42
     commend
    0.41
     regain
    0.40
     barely
    0.38
     বাঙ্গালীর
    0.38
    便是
    0.38
     cursory
    0.38
     abhor
    0.38
     तुमसे
    0.38
    hi
    0.37
    Activations Density 0.000%

    No Known Activations