© 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. 206907
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    afficher
    0.42
    ヒル
    0.41
    Hill
    0.41
    Hil
    0.41
    itemconfig
    0.40
    சிரியர்
    0.40
     создания
    0.38
    ฮ
    0.38
     hil
    0.38
    hills
    0.38
    POSITIVE LOGITS
    left
    0.41
     vf
    0.41
    dashed
    0.41
    dict
    0.39
    pute
    0.38
    ਦ
    0.37
    bing
    0.37
     Das
    0.36
     izquierda
    0.36
    openg
    0.35
    Activations Density 0.003%

    No Known Activations