© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61722
    Prev
    Next
    INDEX
    Explanations

    start of word 't'

    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_2_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
    0.99
     μιας
    0.92
     excellente
    0.86
     oficio
    0.86
     एमटीएस
    0.85
     hérit
    0.84
    ন
    0.84
     affirme
    0.84
    Entonces
    0.83
    ที่
    0.82
    POSITIVE LOGITS
    g
    1.06
    ᱶ
    0.98
    m
    0.97
    。
    0.96
    आई
    0.95
    ᆸ
    0.94
    هر
    0.89
    ᆷ
    0.86
    r
    0.84
     flooded
    0.84
    Activations Density 0.000%

    No Known Activations