© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86908
    Prev
    Next
    INDEX
    Explanations

    impurities, Ravalomanana, cards, clusters

    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
    0
    0.58
    ，
    0.54
    <0x0D>
    0.53
    ni
    0.49
    να
    0.48
    res
    0.46
    ost
    0.46
     s
    0.45
    li
    0.44
     N
    0.43
    POSITIVE LOGITS
     trataro
    0.50
     ассорти
    0.50
     восем
    0.49
    橑
    0.48
     прибыль
    0.48
    hiddenMap
    0.46
    ദന
    0.46
     выбрали
    0.46
     антенна
    0.46
    дж
    0.46
    Activations Density 0.000%

    No Known Activations