© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 131038
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and state variables

    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_25_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
     справ
    0.38
     widest
    0.36
     broad
    0.35
    ूँ
    0.35
     Rosemary
    0.35
     tyle
    0.34
    ─
    0.33
     strengthening
    0.33
     sci
    0.33
     Rein
    0.33
    POSITIVE LOGITS
    raum
    0.40
    ölt
    0.40
    orschungs
    0.40
    hesk
    0.39
     doet
    0.39
    晎
    0.38
    STRING
    0.38
    agre
    0.37
     люб
    0.37
    aktion
    0.36
    Activations Density 0.000%

    No Known Activations