© 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. 129596
    Prev
    Next
    INDEX
    Explanations

    dynamic content placeholders

    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
     दर्जन
    0.42
     указа
    0.38
     '?
    0.38
    巳
    0.37
     dozen
    0.37
     Ararat
    0.37
     yac
    0.36
     DNIs
    0.36
     Indications
    0.35
    内外
    0.35
    POSITIVE LOGITS
    ຖານ
    0.39
     étudiants
    0.38
     മത്സ
    0.38
    ]|[
    0.38
     aján
    0.38
     ferromagnetic
    0.37
     dzī
    0.37
    რობ
    0.37
    㸮
    0.37
     pezzi
    0.37
    Activations Density 0.000%

    No Known Activations