© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165278
    Prev
    Next
    INDEX
    Explanations

    ary

    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_31_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
     تسم
    0.44
    atform
    0.41
    Recurs
    0.38
     জন্
    0.38
    Importance
    0.37
    Birth
    0.37
    invasive
    0.37
    𝙶
    0.36
    Poppins
    0.35
     Mew
    0.35
    POSITIVE LOGITS
     comportamiento
    0.45
     comportamento
    0.45
     безо
    0.37
     comunicación
    0.36
     academ
    0.36
     libros
    0.36
    月号
    0.36
     disseminate
    0.36
     personas
    0.36
     documentos
    0.36
    Activations Density 0.009%

    No Known Activations