© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136441
    Prev
    Next
    INDEX
    Explanations

    bias perpetuate

    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_37_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
    iliar
    0.39
    iculate
    0.39
    煨
    0.38
    ötet
    0.38
     inhibition
    0.38
    шением
    0.37
     quint
    0.36
     эми
    0.36
     Espanha
    0.36
    环
    0.36
    POSITIVE LOGITS
    Trust
    0.43
     trust
    0.42
     Hamlet
    0.42
    TRUST
    0.42
     perpetuate
    0.41
    trust
    0.40
     중요하다
    0.40
     մե
    0.39
     جائے
    0.38
     Trust
    0.38
    Activations Density 0.013%

    No Known Activations