© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175395
    Prev
    Next
    INDEX
    Explanations

    illustrate:

    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_20_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
     काउंसलिंग
    0.38
    commitment
    0.38
     electrification
    0.37
     Ф
    0.35
     campaigning
    0.35
    moil
    0.35
    falt
    0.35
     crucifixion
    0.35
     💪
    0.35
    ಿತ್ತು
    0.35
    POSITIVE LOGITS
    رس
    0.36
    ن
    0.34
     దీని
    0.32
    ជន
    0.32
     రూప
    0.32
     حذف
    0.32
     சரி
    0.31
    չ
    0.31
    பாவ
    0.31
    Vendor
    0.31
    Activations Density 0.005%

    No Known Activations