© 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. 200298
    Prev
    Next
    INDEX
    Explanations

    out loud

    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
    GISLATIVE
    0.49
     lysates
    0.48
    ])):
    0.47
     dirigir
    0.47
    𝑠
    0.47
    ])),
    0.47
     conduits
    0.47
     ペンダント
    0.46
     catalysis
    0.46
     catalysts
    0.46
    POSITIVE LOGITS
    poco
    0.60
     futura
    0.57
     aggi
    0.55
    nije
    0.54
    casa
    0.54
     உயிர்
    0.53
    nese
    0.52
    追加
    0.52
    House
    0.52
    3
    0.52
    Activations Density 0.000%

    No Known Activations