© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197855
    Prev
    Next
    INDEX
    Explanations

    term of the agreement

    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_27_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
    的确
    0.43
    釗
    0.40
    賚
    0.39
     عين
    0.39
    荚
    0.39
     تعلیم
    0.38
    ഐ
    0.38
    額
    0.37
    確かに
    0.37
    െങ്കിൽ
    0.37
    POSITIVE LOGITS
     indulge
    0.38
     Plattform
    0.37
     tudo
    0.36
     любых
    0.36
     asociaciones
    0.36
     Pulp
    0.35
    ревнова
    0.35
     manipulate
    0.35
     সংস
    0.35
     하며
    0.35
    Activations Density 0.000%

    No Known Activations