© 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. 2847
    Prev
    Next
    INDEX
    Explanations

    segments

    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
     લખ
    0.52
     لکھ
    0.51
     escrever
    0.49
     escribió
    0.49
    Write
    0.47
     写
    0.46
     Write
    0.45
    写
    0.45
     لکھا
    0.44
     写真
    0.43
    POSITIVE LOGITS
     segment
    1.44
     segments
    1.32
    segment
    1.28
     Segment
    1.22
     segmentos
    1.22
     segmento
    1.20
    segments
    1.20
    Segment
    1.19
     сег
    1.09
    Segments
    1.02
    Activations Density 0.116%

    No Known Activations