© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215666
    Prev
    Next
    INDEX
    Explanations

    academic fields and -ism suffixes

    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_5_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
    of
    1.48
    er
    1.22
    리
    1.18
    um
    1.09
    ール
    1.08
    のは
    1.07
     the
    1.05
    ない
    1.04
    ed
    1.02
    ী
    1.02
    POSITIVE LOGITS
    l
    0.96
    ی
    0.93
    ς
    0.88
     [(
    0.83
    ؟.
    0.83
     распростран
    0.82
    ētu
    0.79
     воспита
    0.79
     -.
    0.78
     ∈
    0.78
    Activations Density 0.002%

    No Known Activations