© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203922
    Prev
    Next
    INDEX
    Explanations

    units of pressure (torr)

    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_6_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
    in
    1.47
    w
    1.13
    ar
    1.13
    ol
    1.13
    ap
    1.07
    ments
    1.04
    il
    1.02
    h
    1.00
    innt
    0.96
    ie
    0.95
    POSITIVE LOGITS
    0.89
    }
    0.89
     slučaj
    0.87
    IS
    0.85
     at
    0.85
     ateş
    0.85
    ]
    0.84
    ID
    0.83
     zemlje
    0.81
     opportunità
    0.80
    Activations Density 0.001%

    No Known Activations