© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121245
    Prev
    Next
    INDEX
    Explanations

    to build, create, or provide

    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
     поступи
    0.33
    দ্ভুত
    0.31
    -'+
    0.31
    鿷
    0.30
    ত্তর
    0.30
    দ্ভ
    0.30
     bled
    0.30
    }}^{(\
    0.30
     pilha
    0.29
     refiere
    0.29
    POSITIVE LOGITS
     Hiring
    0.31
     Add
    0.30
     बताना
    0.30
     вмі
    0.29
     Tasty
    0.29
    ริม
    0.29
     Paying
    0.28
     Observing
    0.28
    overy
    0.28
     Interests
    0.28
    Activations Density 0.006%

    No Known Activations