© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106175
    Prev
    Next
    INDEX
    Explanations

    hey followed by greeting

    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_1_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
    ۵
    1.50
    ５
    1.18
    ４
    1.16
    ٣
    1.09
    ४
    1.07
    ジ
    1.05
    5
    1.05
     navegación
    1.04
    ティ
    1.02
    𝘀
    1.02
    POSITIVE LOGITS
    ני
    1.08
     it
    1.01
     It
    1.00
     COMPANY
    0.96
     "+
    0.96
     VARCHAR
    0.96
    rt
    0.93
     That
    0.91
    í
    0.89
    oring
    0.89
    Activations Density 0.001%

    No Known Activations