© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98452
    Prev
    Next
    INDEX
    Explanations

    The immortal jellyfish *Turritopsis dohrnii*

    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_14_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
     आउट
    0.58
     quinquina
    0.56
    畱
    0.55
     неф
    0.52
     १६
    0.52
     पीना
    0.52
     couvrir
    0.51
     minyak
    0.50
     อาจารย์
    0.50
     धनिया
    0.50
    POSITIVE LOGITS
    ________________
    0.58
    generate
    0.57
    _______________
    0.55
     deceler
    0.54
    *
    0.53
    न्ड
    0.52
    要
    0.51
    params
    0.50
    make
    0.50
    ad
    0.50
    Activations Density 0.000%

    No Known Activations