© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118283
    Prev
    Next
    INDEX
    Explanations

    name and username input fields

    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
    βο
    0.43
     источ
    0.40
     ആശ
    0.40
    𝔬
    0.40
    রুদ্ধ
    0.39
     MongoDB
    0.38
     کہانی
    0.38
    Translatef
    0.38
    પૂર્ણ
    0.38
    ChatMessage
    0.37
    POSITIVE LOGITS
    \*
    0.42
    orientation
    0.41
    email
    0.38
     alto
    0.38
     \*
    0.38
     tenor
    0.37
    included
    0.37
     Stirling
    0.36
     caer
    0.36
    www
    0.36
    Activations Density 0.001%

    No Known Activations