© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11662
    Prev
    Next
    INDEX
    Explanations

    business partnerships and entities

    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
    </div>
    0.46
    aining
    0.44
    kay
    0.44
     ヤ
    0.43
    𝑬
    0.42
    mittel
    0.41
    𝗚
    0.41
     نقول
    0.40
    blichen
    0.40
     カ
    0.40
    POSITIVE LOGITS
     pedibus
    0.46
    非常
    0.45
    굉
    0.45
     virksom
    0.44
    ती
    0.43
     audioEngine
    0.43
     apropri
    0.42
    ዥ
    0.41
     veg
    0.41
    자에
    0.41
    Activations Density 0.009%

    No Known Activations