© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138867
    Prev
    Next
    INDEX
    Explanations

    eventually

    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_12_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
    XVI
    0.49
     Handic
    0.45
     মাধ
    0.44
    SCE
    0.44
    Ampl
    0.43
    Sem
    0.43
    Rol
    0.43
    ﺄ
    0.43
    >,
    0.42
    SU
    0.42
    POSITIVE LOGITS
     restaurants
    0.54
     restaurant
    0.49
     restaurante
    0.49
     c
    0.48
     inter
    0.48
     segurança
    0.48
     restaurantes
    0.46
     resposta
    0.46
     charge
    0.44
     interp
    0.44
    Activations Density 0.001%

    No Known Activations