© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3042
    Prev
    Next
    INDEX
    Explanations

    code additions and explanations

    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_40_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
    ioides
    0.40
    Vox
    0.33
    বারের
    0.33
    terdam
    0.32
    ributors
    0.32
    ጀ
    0.32
    ॅप
    0.31
    ຼ
    0.31
    腆
    0.31
    mények
    0.31
    POSITIVE LOGITS
     added
    2.55
     доба
    2.42
     adding
    2.39
     добав
    2.34
     добавля
    2.33
     добавить
    2.30
     Added
    2.27
     Adding
    2.27
    added
    2.23
    添加
    2.23
    Activations Density 0.281%

    No Known Activations