© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172269
    Prev
    Next
    INDEX
    Explanations

    indices assignment

    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
     Frazier
    0.43
    escu
    0.42
     quadrants
    0.41
     nods
    0.41
     स्मरण
    0.41
     G
    0.41
     Stout
    0.40
     feasibility
    0.39
     стен
    0.39
    aver
    0.38
    POSITIVE LOGITS
     którym
    0.47
    []);
    0.46
    ]]);
    0.46
     ಬಂದ
    0.45
     whiche
    0.44
    及时
    0.44
     वापस
    0.44
    Ѳ
    0.43
    lardır
    0.43
     reale
    0.41
    Activations Density 0.002%

    No Known Activations