© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215212
    Prev
    Next
    INDEX
    Explanations

    web links, content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     marble
    0.47
     PCT
    0.41
     moulding
    0.39
     marm
    0.39
    ിലാണ്
    0.39
    鸞
    0.38
    Marble
    0.38
    राजा
    0.38
     गोद
    0.38
    钽
    0.38
    POSITIVE LOGITS
     Avner
    0.39
    𝑭
    0.38
     দি
    0.37
    ítica
    0.37
    Jon
    0.36
    avier
    0.36
    binary
    0.36
    giore
    0.35
    ផុត
    0.35
    照顧
    0.35
    Activations Density 0.011%

    No Known Activations