© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205229
    Prev
    Next
    INDEX
    Explanations

    1

    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
    Clo
    0.47
    clo
    0.41
    ிறார்கள்
    0.39
     Суриков
    0.39
     khởi
    0.37
    usak
    0.37
    狄
    0.36
     impres
    0.36
     cloak
    0.36
    install
    0.36
    POSITIVE LOGITS
     Carefully
    0.42
    |}{
    0.40
     carefully
    0.40
     duplication
    0.40
     ذخ
    0.37
    蛳
    0.37
     stocked
    0.36
    രിക
    0.36
     stockpile
    0.36
    ]_{
    0.36
    Activations Density 0.004%

    No Known Activations