© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197803
    Prev
    Next
    INDEX
    Explanations

    timed exclusives

    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
     Tennessee
    0.44
    必
    0.44
    Chromatic
    0.43
     అయితే
    0.42
    ში
    0.40
     기본적인
    0.40
    我们
    0.40
    Talk
    0.40
    不幸
    0.39
     Obstetrics
    0.39
    POSITIVE LOGITS
    cein
    0.54
    splunk
    0.51
    érc
    0.50
    ﻃ
    0.50
     datas
    0.50
     preferentially
    0.50
     ferramenta
    0.50
    媳
    0.50
    erex
    0.49
     zelo
    0.49
    Activations Density 0.000%

    No Known Activations