© 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. 138031
    Prev
    Next
    INDEX
    Explanations

    transform: rotate, url, translateY, translateX

    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
    ações
    0.25
    蕖
    0.21
    ambique
    0.21
    lik
    0.21
    λή
    0.20
     cryptographic
    0.20
    departments
    0.20
    ação
    0.20
    =")"
    0.19
    اً
    0.19
    POSITIVE LOGITS
     mejor
    0.21
     pravi
    0.21
     जीत
    0.21
    setMaximum
    0.20
     Últ
    0.20
    தில்
    0.20
     caliente
    0.20
     ተጨማሪ
    0.20
     gewann
    0.20
    Markets
    0.20
    Activations Density 0.002%

    No Known Activations