© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15052
    Prev
    Next
    INDEX
    Explanations

    barren land

    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_15_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
    \
    0.56
     изготовления
    0.50
     добиться
    0.50
     detonations
    0.49
     horário
    0.48
     menghindari
    0.48
     hola
    0.48
     crucifix
    0.48
     сами
    0.46
     ей
    0.45
    POSITIVE LOGITS
    𝘺
    0.56
     Valves
    0.54
     Automated
    0.50
    පු
    0.50
    YOUR
    0.49
    from
    0.48
    लेरिया
    0.48
     Serviços
    0.48
    莱
    0.48
     Speaks
    0.48
    Activations Density 0.000%

    No Known Activations