© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43189
    Prev
    Next
    INDEX
    Explanations

    clear text and fonts

    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_13_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
    雪
    0.50
    шка
    0.49
    ic
    0.47
    snow
    0.46
    wald
    0.45
    经验
    0.44
    embangkan
    0.44
     aé
    0.43
     ग्ला
    0.42
    ança
    0.42
    POSITIVE LOGITS
     same
    0.54
     stessi
    0.46
     liberally
    0.45
     .
    0.44
     applied
    0.44
     are
    0.44
     who
    0.44
    APs
    0.43
    )
    0.43
     ফেলে
    0.42
    Activations Density 0.043%

    No Known Activations