© 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. 220470
    Prev
    Next
    INDEX
    Explanations

    don't leave out

    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
     booming
    0.39
    瓢
    0.39
     Spoon
    0.38
     Twice
    0.38
    domin
    0.38
    viv
    0.38
    undet
    0.37
    oliv
    0.37
     pounding
    0.37
     shoal
    0.37
    POSITIVE LOGITS
     obstru
    0.44
    ском
    0.39
     सदर
    0.39
    дание
    0.39
     সুন্নত
    0.39
     Hazards
    0.38
    Ϝ
    0.38
     ]),
    0.38
    ｆ
    0.37
     '|')
    0.37
    Activations Density 0.002%

    No Known Activations