© 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
    2. Gemma-3-27B-IT
    3. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 15949
    Prev
    Next
    INDEX
    Explanations

    bundlers and module formats

    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_34_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
     мото
    0.40
     motoc
    0.37
    ീല
    0.37
     करे
    0.36
     motocicleta
    0.36
     TIT
    0.35
    UPD
    0.35
    锋
    0.34
     मोटरसाइकिल
    0.34
    拨
    0.34
    POSITIVE LOGITS
     dive
    0.43
     cultured
    0.38
    ĕç
    0.38
    hxx
    0.38
     dives
    0.37
    监听
    0.36
     immobilized
    0.36
     Norris
    0.35
     listener
    0.35
     herz
    0.35
    Activations Density 0.008%

    No Known Activations