© 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. 106041
    Prev
    Next
    INDEX
    Explanations

    own your

    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
    ле
    1.41
    it
    1.32
    on
    1.30
    t
    1.30
    ن
    1.29
    ra
    1.27
    ار
    1.26
    ad
    1.24
    ut
    1.23
    ת
    1.22
    POSITIVE LOGITS
    :
    0.96
     dismantled
    0.93
    是我们
    0.93
     যেটি
    0.90
     불구
    0.89
     <
    0.89
    acies
    0.89
    OL
    0.88
    aking
    0.83
     tangled
    0.83
    Activations Density 0.000%

    No Known Activations