© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 196600
    Prev
    Next
    INDEX
    Explanations

    ulse

    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_9_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
    an
    1.39
     D
    1.05
     L
    1.02
     A
    0.99
    k
    0.98
    าย
    0.97
     R
    0.97
     V
    0.96
     sacrament
    0.95
     I
    0.90
    POSITIVE LOGITS
    й
    1.18
    ﺐ
    1.13
    м
    1.13
    م
    1.12
    ޏ
    1.07
     पद्धतीने
    1.05
    мб
    1.05
    ONS
    1.04
    র
    1.04
    ﻢ
    1.03
    Activations Density 0.008%

    No Known Activations