© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151194
    Prev
    Next
    INDEX
    Explanations

    strength, confidence, likelihood, or scale

    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_23_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
    ｪ
    0.31
    unków
    0.30
     شہریوں
    0.30
     ቡ
    0.30
     habite
    0.30
     quilts
    0.28
    𝘢
    0.28
     lamp
    0.28
    ካ
    0.28
    锋
    0.28
    POSITIVE LOGITS
    얕
    0.34
     requerido
    0.31
    Xiaomi
    0.30
     Xiaomi
    0.29
    olska
    0.29
    льзя
    0.28
    ERRORTYPE
    0.28
    மின்றி
    0.28
    所需的
    0.27
     الأحمر
    0.27
    Activations Density 0.005%

    No Known Activations