© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215028
    Prev
    Next
    INDEX
    Explanations

    story titles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     routine
    0.41
    િલ્
    0.41
    바
    0.40
    }!
    0.39
     inc
    0.38
     சா
    0.38
    ੯
    0.38
    சா
    0.37
     тер
    0.37
    Unary
    0.36
    POSITIVE LOGITS
     cosines
    0.44
    ുകൊ
    0.43
    offrey
    0.41
    aisen
    0.40
     Mormon
    0.39
     كوس
    0.39
    
    0.38
    umiem
    0.38
     Koe
    0.38
    inuous
    0.37
    Activations Density 0.000%

    No Known Activations