© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168326
    Prev
    Next
    INDEX
    Explanations

    replacing

    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_56_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
     å
    0.70
     Å
    0.58
    Å
    0.56
    å
    0.53
    آ
    0.46
    ﻵ
    0.46
    ﺁ
    0.41
     آ
    0.41
     Bryson
    0.41
     ஆ
    0.41
    POSITIVE LOGITS
     replaces
    0.46
     replaced
    0.43
     replacing
    0.42
     replace
    0.41
    Already
    0.40
     sostitu
    0.40
     замі
    0.39
     thanks
    0.39
    replace
    0.39
    Get
    0.39
    Activations Density 0.000%

    No Known Activations