© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215538
    Prev
    Next
    INDEX
    Explanations

    Blankenhorn, Kangchenjunga, Denon

    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
     aback
    0.41
    тил
    0.39
    यन
    0.38
    тного
    0.37
    㕶
    0.37
    禟
    0.36
    ວ່າ
    0.36
    ؍
    0.36
    eted
    0.36
     Francesco
    0.36
    POSITIVE LOGITS
     硬
    0.43
     operandSize
    0.40
    meri
    0.39
    赛季
    0.38
    health
    0.37
    硬
    0.37
     :]
    0.37
    年輕
    0.36
    Totally
    0.36
    Automatically
    0.36
    Activations Density 0.018%

    No Known Activations