© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40749
    Prev
    Next
    INDEX
    Explanations

    the only, the preservation, the reason, the cause, the place, the joy, the thing

    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
     out
    0.63
    ا
    0.62
    ults
    0.59
     anticipated
    0.59
     estrogen
    0.59
     allergy
    0.57
     auditions
    0.57
     eats
    0.56
     vacations
    0.56
     į
    0.55
    POSITIVE LOGITS
    followlike
    0.68
     Algun
    0.68
     Verme
    0.63
     Menschen
    0.63
     Kindern
    0.63
    JScripts
    0.63
     Boga
    0.63
    ló
    0.61
    }]}\
    0.61
     kleinere
    0.61
    Activations Density 0.009%

    No Known Activations