© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141567
    Prev
    Next
    INDEX
    Explanations

    uproar, outcry, yell, crowd

    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
    ícito
    0.50
    憤
    0.48
     públic
    0.48
    érir
    0.47
     krzy
    0.47
     shouting
    0.47
    ériel
    0.46
    éssel
    0.46
    aufen
    0.45
    ügel
    0.45
    POSITIVE LOGITS
    a
    0.53
    addy
    0.51
    𝑎
    0.51
     Skyscrapers
    0.50
     Stairs
    0.50
    uk
    0.48
     Испа
    0.47
    ak
    0.47
    ૃહ
    0.46
    𝑅
    0.46
    Activations Density 0.001%

    No Known Activations