© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166335
    Prev
    Next
    INDEX
    Explanations

    pygame.display.flip()

    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_34_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
     Prolong
    0.41
     மான
    0.39
    ovana
    0.39
    Kitchen
    0.38
     Tinder
    0.38
     उबाल
    0.37
    吃
    0.37
     windscreen
    0.37
     kitchen
    0.36
    deposit
    0.36
    POSITIVE LOGITS
     posisi
    0.41
     масси
    0.39
    の位置
    0.38
    󰡕
    0.38
     fabricating
    0.37
    fest
    0.37
     posiciones
    0.37
     disseminating
    0.37
    pmod
    0.36
    IndexArray
    0.36
    Activations Density 0.001%

    No Known Activations