© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34547
    Prev
    Next
    INDEX
    Explanations

    code punctuation } : )

    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_31_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
    Summary
    0.23
    RECEIVED
    0.22
     ю
    0.21
    हू
    0.21
    బాటు
    0.21
    arrayList
    0.21
    Ю
    0.20
     Definitely
    0.20
    尤
    0.20
     least
    0.20
    POSITIVE LOGITS
     queremos
    0.24
    ibhav
    0.23
     Unterstützung
    0.23
     sorular
    0.23
    čky
    0.23
     chiede
    0.22
     incógn
    0.22
     estudiar
    0.22
     Kiwi
    0.22
     thermometers
    0.22
    Activations Density 0.004%

    No Known Activations