© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151135
    Prev
    Next
    INDEX
    Explanations

    company names/brands

    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_60_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
    版本
    0.38
     translator
    0.37
     differs
    0.37
     {|
    0.37
     capacities
    0.36
     repetitions
    0.36
     need
    0.36
    Pw
    0.36
     besoins
    0.36
    Forgery
    0.35
    POSITIVE LOGITS
     Challeng
    0.44
     moeil
    0.42
     ਵਰ
    0.42
    ermi
    0.42
    alah
    0.41
    ISTS
    0.40
    寧
    0.40
    IMAL
    0.39
     DIFFIC
    0.39
    宁
    0.38
    Activations Density 0.005%

    No Known Activations