© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89611
    Prev
    Next
    INDEX
    Explanations

    in followed by a word

    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
    级别的
    0.12
    鐧
    0.12
    㑒
    0.11
    はこの
    0.11
    鋈
    0.11
    analysis
    0.11
    وراق
    0.11
    κή
    0.11
    匼
    0.11
     قناه
    0.11
    POSITIVE LOGITS
     OB
    0.12
     a
    0.11
     es
    0.11
    OB
    0.11
     Bre
    0.10
     Landry
    0.10
     Pro
    0.10
     potenti
    0.10
     Existen
    0.10
    Uno
    0.10
    Activations Density 0.128%

    No Known Activations