© 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. 138424
    Prev
    Next
    INDEX
    Explanations

    to [verb] / expects to [verb]

    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
    homotopic
    0.59
     elaboración
    0.57
     eliminación
    0.57
    geç
    0.57
    발
    0.56
    ِين
    0.55
    gambar
    0.55
    carriage
    0.54
     adquisición
    0.54
    move
    0.54
    POSITIVE LOGITS
     n
    0.64
     krit
    0.60
     bearded
    0.59
    0.59
     k
    0.57
     smelt
    0.57
     als
    0.57
     wollte
    0.57
    ו
    0.57
     gesch
    0.56
    Activations Density 0.001%

    No Known Activations