© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 149089
    Prev
    Next
    INDEX
    Explanations

    endocardial, calomel, radial strength

    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_18_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
    h
    0.68
    m
    0.66
    mm
    0.65
    mL
    0.60
    k
    0.59
    cm
    0.58
    md
    0.57
    schl
    0.55
    mons
    0.55
    p
    0.54
    POSITIVE LOGITS
     interrom
    0.46
     установи
    0.46
    ری
    0.45
     изменя
    0.45
    闿
    0.45
     occurring
    0.44
     вмеша
    0.44
     impossibile
    0.43
    ஸ்வர
    0.43
     மூலம்
    0.43
    Activations Density 0.000%

    No Known Activations