© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161390
    Prev
    Next
    INDEX
    Explanations

    principal components, principal paid, principal deity

    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_2_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
    д
    1.30
    quela
    1.04
    ای
    1.01
    ouro
    1.01
    ocèle
    1.01
    èdent
    0.99
    гана
    0.97
     άλλ
    0.96
    них
    0.96
    ोष
    0.96
    POSITIVE LOGITS
    a
    2.03
    0
    1.72
     a
    1.64
    j
    1.63
    ir
    1.61
    i
    1.56
    in
    1.53
    g
    1.51
    ii
    1.48
    l
    1.44
    Activations Density 0.001%

    No Known Activations