© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135720
    Prev
    Next
    INDEX
    Explanations

    definitely, certainty, or guaranteed truth

    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_37_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
    배
    0.36
     डिलिवरी
    0.35
    ܀
    0.35
     espect
    0.35
    PPE
    0.33
    venidas
    0.33
    ردو
    0.33
    emples
    0.32
     муниципального
    0.32
    근
    0.32
    POSITIVE LOGITS
     definitely
    1.99
     Definitely
    1.77
    Definitely
    1.73
     definitiv
    1.71
     kesin
    1.63
     definitivamente
    1.60
     확실
    1.48
    確実に
    1.47
     zeker
    1.42
    แน่นอน
    1.41
    Activations Density 0.227%

    No Known Activations