© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80660
    Prev
    Next
    INDEX
    Explanations

    computer science authors

    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_53_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
     الكويت
    0.39
     መድ
    0.38
    ндарт
    0.38
     methodical
    0.37
     moderna
    0.37
    齦
    0.37
    ProgressBar
    0.37
    ணற
    0.36
     watching
    0.36
    れない
    0.36
    POSITIVE LOGITS
     NIM
    0.43
     Speak
    0.42
    パク
    0.41
     Nicholls
    0.40
    desIP
    0.39
     Plugin
    0.38
    ظل
    0.38
    %>%
    0.38
     spool
    0.38
     Nimbus
    0.38
    Activations Density 0.000%

    No Known Activations