© 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. 89661
    Prev
    Next
    INDEX
    Explanations

    content after appeal

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     başkan
    0.43
     okt
    0.43
     resistencias
    0.42
    境界層
    0.41
     resistances
    0.40
    睃
    0.40
     طب
    0.40
     \%
    0.40
     später
    0.40
    opathic
    0.39
    POSITIVE LOGITS
    Vivo
    0.41
    confirm
    0.39
    getContext
    0.38
    Muslim
    0.38
    Siem
    0.38
    did
    0.38
     Luisa
    0.38
    Hors
    0.38
    harvest
    0.37
     Indie
    0.37
    Activations Density 0.000%

    No Known Activations