© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148339
    Prev
    Next
    INDEX
    Explanations

    say "main"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    er
    0.42
    phoneNumber
    0.38
    ẻ
    0.37
     जी
    0.36
     ]),
    0.36
    եր
    0.36
    espa
    0.36
     End
    0.35
    }^{\#
    0.35
    prü
    0.35
    POSITIVE LOGITS
     solve
    0.46
     destroy
    0.43
     consume
    0.42
     earn
    0.41
    most
    0.41
     main
    0.39
     battle
    0.39
     create
    0.39
     catalyze
    0.39
    ούμε
    0.38
    Activations Density 0.003%

    No Known Activations