© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5382
    Prev
    Next
    INDEX
    Explanations

    dates and durations

    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_39_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
    ající
    0.27
     stargazerCount
    0.27
     घन
    0.26
    ันทร์
    0.26
     большой
    0.26
     coleção
    0.26
    偻
    0.26
    壹百
    0.25
     नाकाम
    0.25
     বৃহৎ
    0.25
    POSITIVE LOGITS
     CTR
    0.26
    Insert
    0.25
    ism
    0.24
     tick
    0.24
    ff
    0.22
    Adder
    0.22
    os
    0.22
     semin
    0.21
    Az
    0.21
    Mir
    0.21
    Activations Density 0.000%

    No Known Activations