© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91654
    Prev
    Next
    INDEX
    Explanations

    is it likely

    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_11_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
    6
    0.54
    8
    0.51
    2
    0.46
    fixed
    0.42
    یدم
    0.42
    visible
    0.41
    TP
    0.40
    fix
    0.40
    ID
    0.40
    separation
    0.40
    POSITIVE LOGITS
     hilft
    0.50
    并
    0.50
     Andrei
    0.47
     değil
    0.47
     devel
    0.46
    有助于
    0.45
    t
    0.45
    sdag
    0.45
     etk
    0.45
     ৪
    0.44
    Activations Density 0.038%

    No Known Activations