© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32713
    Prev
    Next
    INDEX
    Explanations

    say "if"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    煜
    0.35
    珬
    0.35
    ੍ਹਾਂ
    0.35
    
    0.35
     alb
    0.34
     διο
    0.34
    ោគ
    0.34
    토
    0.34
    ଲା
    0.34
     lLoginID
    0.34
    POSITIVE LOGITS
     IF
    3.06
    IF
    2.83
     IFC
    2.19
     IFN
    1.98
     आईएफ
    1.98
     ifs
    1.92
    if
    1.89
    ifs
    1.87
     इफ
    1.84
     IFA
    1.84
    Activations Density 0.577%

    No Known Activations