© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117541
    Prev
    Next
    INDEX
    Explanations

    can you explain/figure/tell

    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_27_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
     シュ
    0.45
    કિસ્
    0.42
     Palt
    0.42
     скорее
    0.41
     renderEncoder
    0.41
    詼
    0.40
    껭
    0.40
     eaves
    0.39
     звуча
    0.39
    Ⴖ
    0.39
    POSITIVE LOGITS
     subscribed
    0.44
     imperfect
    0.40
     embraced
    0.40
     param
    0.39
    散
    0.38
    待
    0.37
    BSC
    0.36
    工程
    0.36
     exercised
    0.35
    goo
    0.35
    Activations Density 0.002%

    No Known Activations