© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158155
    Prev
    Next
    INDEX
    Explanations

    hemoglobin and myoglobin concentration

    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_2_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
    it
    2.20
    a
    1.74
    c
    1.50
    as
    1.47
    o
    1.46
    an
    1.40
    os
    1.39
    ri
    1.39
    rt
    1.34
    ik
    1.32
    POSITIVE LOGITS
     user
    1.30
     war
    1.20
     white
    1.18
     insult
    1.16
    ม
    1.09
     name
    1.08
     remote
    1.08
     home
    1.03
    </h3>
    1.02
     device
    1.02
    Activations Density 0.000%

    No Known Activations