© 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
    2. Gemma-3-27B-IT
    3. 4-GEMMASCOPE-2-TRANSCODER-262K
    4. 195848
    Prev
    Next
    INDEX
    Explanations

    loans, directory paths, or search

    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_4_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
    Y
    0.25
    in
    0.25
    er
    0.23
    Z
    0.21
    OL
    0.21
    OTS
    0.20
    at
    0.20
    to
    0.20
    UL
    0.20
     of
    0.19
    POSITIVE LOGITS
     an
    0.18
     singularities
    0.16
     aler
    0.15
     कर्तव्यों
    0.15
     значение
    0.14
     ailing
    0.14
    ன
    0.14
     δεδο
    0.14
     sbag
    0.14
    ம்
    0.14
    Activations Density 0.005%

    No Known Activations