© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214781
    Prev
    Next
    INDEX
    Explanations

    approximately or around

    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_50_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
    ಉ
    0.42
     over
    0.40
     hierarchical
    0.40
    pointers
    0.39
     pointers
    0.39
     coercive
    0.39
     statutory
    0.38
    过
    0.38
     lounges
    0.37
     niches
    0.37
    POSITIVE LOGITS
    ின்றான்
    0.43
     Neces
    0.43
    منت
    0.42
     settimana
    0.41
     tentativo
    0.40
     Fut
    0.39
     bolas
    0.39
     Dis
    0.39
     bole
    0.38
     favorita
    0.38
    Activations Density 0.006%

    No Known Activations