© 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. 136399
    Prev
    Next
    INDEX
    Explanations

    compressive strength

    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
    合同
    0.44
    LaTeX
    0.44
    Contract
    0.42
     lavor
    0.40
     Mixing
    0.40
     Contract
    0.39
     dough
    0.38
    輾
    0.38
     trabajar
    0.37
    ats
    0.37
    POSITIVE LOGITS
     कार्ब
    0.39
    鈴
    0.38
    sampled
    0.37
    assay
    0.37
    ትክል
    0.36
    ชี
    0.36
     दू
    0.36
     platoon
    0.36
     KUM
    0.36
     Karam
    0.36
    Activations Density 0.001%

    No Known Activations