© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80274
    Prev
    Next
    INDEX
    Explanations

    end of sentence

    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_53_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
     closeup
    0.41
    ള്ളി
    0.40
     dajj
    0.40
     لیګ
    0.38
    crollView
    0.38
    ्योपै
    0.38
    ږئ
    0.37
    ⿲
    0.37
    sqcup
    0.36
    प्तान
    0.36
    POSITIVE LOGITS
    Ві
    0.36
    ங்க
    0.34
    াকার
    0.34
    etics
    0.34
     कितना
    0.34
    琇
    0.34
    <b>
    0.34
     টিক
    0.34
     Ulysses
    0.33
     নিম্নলিখিত
    0.32
    Activations Density 0.002%

    No Known Activations