© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30590
    Prev
    Next
    INDEX
    Explanations

    question answer structure

    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_7_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
    if
    0.42
    ها
    0.40
    بار
    0.39
    রাও
    0.39
    Change
    0.38
    $,
    0.37
    عل
    0.36
    Мен
    0.35
    علوم
    0.35
    Count
    0.35
    POSITIVE LOGITS
     in
    0.52
     was
    0.51
     were
    0.49
     to
    0.47
     optimally
    0.44
    𝘀
    0.44
     is
    0.43
    ,
    0.43
     can
    0.42
     will
    0.40
    Activations Density 0.004%

    No Known Activations