© 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. 14669
    Prev
    Next
    INDEX
    Explanations

    ions

    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
     varphi
    0.63
     ditth
    0.63
     feedwater
    0.62
     방법을
    0.62
     листья
    0.62
     플
    0.61
     Prothorax
    0.60
     diphenyl
    0.60
    詼
    0.60
     álgebra
    0.60
    POSITIVE LOGITS
    -
    0.60
    count
    0.57
    uman
    0.52
    uan
    0.51
    ”
    0.51
    sum
    0.51
    /*
    0.51
    neq
    0.50
    ’
    0.50
    atu
    0.50
    Activations Density 0.004%

    No Known Activations