© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216076
    Prev
    Next
    INDEX
    Explanations

    say "testing"

    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_47_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
     invade
    0.40
     কট
    0.39
     fabricate
    0.39
     devaluation
    0.38
     vampire
    0.38
    hemeral
    0.38
     etmektedir
    0.37
    靗
    0.37
    लभ
    0.37
    ாலின்
    0.36
    POSITIVE LOGITS
    тени
    0.39
     tension
    0.38
     Tension
    0.38
    ional
    0.37
    őt
    0.36
    緊張
    0.36
    )¶
    0.36
    tension
    0.36
    紧张
    0.35
    ksjon
    0.35
    Activations Density 0.001%

    No Known Activations