© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246632
    Prev
    Next
    INDEX
    Explanations

    set_missing_host_key_policy

    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_40_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
     backups
    0.41
     recursion
    0.37
    Isra
    0.36
     backup
    0.36
    ୂ
    0.36
     成分
    0.36
     ያስ
    0.35
     менее
    0.35
     quadri
    0.35
     ကု
    0.34
    POSITIVE LOGITS
     Diam
    0.42
     जम
    0.40
     gist
    0.39
    ною
    0.37
     nevez
    0.37
     تیز
    0.36
    ట్టి
    0.36
     Soap
    0.36
    ="<?=
    0.35
     Prem
    0.34
    Activations Density 0.000%

    No Known Activations