© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207428
    Prev
    Next
    INDEX
    Explanations

    Gettysburg Address and Battlefield

    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_20_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
     cap
    0.41
    modelo
    0.41
    ბ
    0.41
    воро
    0.40
    ජ
    0.40
     الرياض
    0.40
    ovac
    0.40
    мести
    0.40
     ज्ये
    0.39
     UE
    0.38
    POSITIVE LOGITS
     konfl
    0.55
     puțin
    0.49
     konflik
    0.48
     Larkin
    0.46
     kötü
    0.44
     hemorrhage
    0.44
     horrific
    0.43
    }}=-\
    0.43
    श्किल
    0.43
    ബർ
    0.43
    Activations Density 0.000%

    No Known Activations