© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    4. 81325
    Prev
    Next
    INDEX
    Explanations

    glomerulonephritis, monotremes, erythrocyte, pyrophosphate, metafiction

    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_0_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
    ल
    2.16
    is
    1.78
    ל
    1.75
    ل
    1.55
    لای
    1.46
    ስ
    1.41
     売場面積
    1.39
    स
    1.34
     axiom
    1.32
    ল
    1.31
    POSITIVE LOGITS
    ä
    1.55
    4
    1.39
    az
    1.34
     hypothes
    1.29
    ,
    1.26
     decentral
    1.25
     synthes
    1.16
    ことを
    1.16
    </h2>
    1.15
    </strong>
    1.13
    Activations Density 0.000%

    No Known Activations