© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50272
    Prev
    Next
    INDEX
    Explanations

    possess a strong

    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_31_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
     ră
    0.42
     regulations
    0.40
     règlement
    0.39
    abhavo
    0.38
     التن
    0.38
    RANGER
    0.38
     limite
    0.37
     칼
    0.37
     فٹ
    0.37
    鋒
    0.37
    POSITIVE LOGITS
     eyeglasses
    0.38
     sensit
    0.38
    Sens
    0.37
    ican
    0.37
     चुके
    0.37
     chc
    0.37
     Requires
    0.37
     buscas
    0.37
    Begin
    0.36
    uña
    0.36
    Activations Density 0.004%

    No Known Activations