© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37428
    Prev
    Next
    INDEX
    Explanations

    disappointed

    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_11_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
    general
    0.68
    esthetic
    0.62
    </em>
    0.57
    bis
    0.57
    bibli
    0.55
     groundwork
    0.55
    다
    0.55
    Referências
    0.55
    Audit
    0.55
    l
    0.55
    POSITIVE LOGITS
     yao
    0.63
     fron
    0.63
     Bharati
    0.61
     fortal
    0.60
     punished
    0.59
     Bohemia
    0.58
     defended
    0.57
     jurisdic
    0.57
    ર
    0.57
     leyenda
    0.55
    Activations Density 0.000%

    No Known Activations