© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137895
    Prev
    Next
    INDEX
    Explanations

    hésitez, j'ai,espère

    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_12_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
    jref
    0.68
    ن
    0.66
    illées
    0.63
    en
    0.60
    uldron
    0.60
     बढ़ती
    0.59
     Wikispecies
    0.59
     সবাই
    0.59
     gahet
    0.58
     Ruhr
    0.58
    POSITIVE LOGITS
    <0xA4>
    0.66
     has
    0.58
     for
    0.56
    чена
    0.55
     doe
    0.54
    od
    0.53
    ים
    0.53
    <0xB1>
    0.53
     possesses
    0.52
    า
    0.50
    Activations Density 0.000%

    No Known Activations