© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38106
    Prev
    Next
    INDEX
    Explanations

    washing, fractions, acetate

    np_acts-logits-general · gemini-2.5-flash-lite

    chemical quantities, units, and reaction conditions.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi

    organic chemistry

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    0
    0.46
     territorio
    0.43
    Customers
    0.39
    चित
    0.39
     marzo
    0.39
    MAS
    0.39
    ляет
    0.38
    Bromo
    0.38
    CTOR
    0.38
    जुर्ग
    0.38
    POSITIVE LOGITS
    ure
    0.45
     OPEC
    0.43
    venue
    0.42
    杰
    0.42
     intu
    0.42
     financement
    0.42
     barges
    0.42
     Haiti
    0.41
     sheer
    0.41
    intu
    0.41
    Activations Density 0.026%

    No Known Activations