© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79888
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    is
    1.95
    ek
    1.56
    m
    1.55
    é
    1.53
    en
    1.51
    il
    1.48
    n
    1.46
    re
    1.44
    ir
    1.39
    et
    1.38
    POSITIVE LOGITS
     is
    1.59
    (
    1.29
     सम्मान
    1.13
    ົບ
    1.12
    {
    1.12
    ご
    1.11
     जबकि
    1.10
    ELL
    1.10
     खासतौर
    1.10
    トン
    1.09
    Activations Density 0.000%

    No Known Activations