© 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. 235926
    Prev
    Next
    INDEX
    Explanations

    code and commands

    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
    нибудь
    0.55
     Nit
    0.50
     nit
    0.49
     nip
    0.47
    نج
    0.45
     NIT
    0.45
     Nih
    0.45
    甯
    0.44
     निधि
    0.43
    nit
    0.42
    POSITIVE LOGITS
     半袖
    0.37
    kli
    0.36
     आश्वासन
    0.36
    таны
    0.36
    Broken
    0.35
    broken
    0.35
    ccin
    0.35
     собственно
    0.34
    below
    0.34
    َال
    0.34
    Activations Density 0.002%

    No Known Activations