© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51210
    Prev
    Next
    INDEX
    Explanations

    object with methods and properties

    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_30_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
     synthesized
    0.23
    Whole
    0.21
     어느
    0.21
    Definitely
    0.20
    อก
    0.19
    luk
    0.19
    ኾ
    0.19
     whole
    0.19
     simulated
    0.19
     quay
    0.19
    POSITIVE LOGITS
    ейчас
    0.27
     সদা
    0.22
    oraus
    0.22
    elitian
    0.21
    药
    0.20
    ецца
    0.20
    autas
    0.20
     gesprek
    0.20
     conmigo
    0.20
     ध्व
    0.20
    Activations Density 0.005%

    No Known Activations