© 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. 137284
    Prev
    Next
    INDEX
    Explanations

    all the issues and requirements

    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
     earlier
    0.43
     ві
    0.41
     sebelumnya
    0.41
     spectrometers
    0.40
    वालों
    0.39
     écr
    0.38
     tidigare
    0.38
    ›
    0.38
     remaining
    0.37
    previous
    0.37
    POSITIVE LOGITS
     detectable
    0.40
     aspectos
    0.40
     राजप
    0.39
     proposto
    0.39
     Tugas
    0.38
    codetest
    0.38
     Depot
    0.37
    examtype
    0.37
    łącznie
    0.37
     ottenuto
    0.37
    Activations Density 0.000%

    No Known Activations