© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138694
    Prev
    Next
    INDEX
    Explanations

    make mistakes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     admission
    0.48
    ∞
    0.45
     Bail
    0.41
    MoveNext
    0.40
    bail
    0.39
     bail
    0.39
    Infinity
    0.38
    āv
    0.38
    ausch
    0.38
     ∞
    0.38
    POSITIVE LOGITS
    洍
    0.44
    ترام
    0.39
     screw
    0.39
     provoca
    0.39
     deras
    0.38
     Madera
    0.38
     만들기
    0.36
    造
    0.36
     만들
    0.36
    Reporting
    0.36
    Activations Density 0.006%

    No Known Activations