© 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. 152861
    Prev
    Next
    INDEX
    Explanations

    baby teeth

    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
    izamos
    0.46
     PRET
    0.46
     TIN
    0.46
    对
    0.45
     Assigned
    0.44
     RES
    0.44
     danh
    0.44
     TRY
    0.43
    untos
    0.43
     ASS
    0.42
    POSITIVE LOGITS
    мі
    0.42
    ("")
    0.40
    내
    0.40
    Inet
    0.38
    should
    0.38
    roomId
    0.37
    podcast
    0.37
    Innen
    0.36
     Gericht
    0.36
    igrants
    0.36
    Activations Density 0.000%

    No Known Activations