© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211390
    Prev
    Next
    INDEX
    Explanations

    build a fort

    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_19_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
     сигнал
    0.44
     attham
    0.41
     fathom
    0.40
     ghế
    0.39
     thigh
    0.39
    얕
    0.38
     sekitar
    0.38
     turistas
    0.38
     lontano
    0.38
     gangs
    0.38
    POSITIVE LOGITS
    मध्ये
    0.40
    _
    0.40
    Declar
    0.39
    ców
    0.39
    Objet
    0.37
     بابەت
    0.36
     Item
    0.36
    sson
    0.36
     Declar
    0.36
    Defense
    0.36
    Activations Density 0.002%

    No Known Activations