© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 62368
    Prev
    Next
    INDEX
    Explanations

    Intel processors and virtualization

    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_41_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
    Living
    0.60
     LIVING
    0.53
    living
    0.52
     Living
    0.51
     लिविंग
    0.49
     living
    0.45
    洳
    0.45
     net
    0.40
     Livingston
    0.40
    Net
    0.39
    POSITIVE LOGITS
     v
    0.69
    v
    0.41
     identities
    0.40
     formations
    0.40
     leiden
    0.40
     gara
    0.39
     Arist
    0.38
     Acc
    0.38
     Schweizer
    0.38
     ident
    0.38
    Activations Density 0.039%

    No Known Activations