© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179999
    Prev
    Next
    INDEX
    Explanations

    `enum class` definitions

    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_24_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
    ┗
    0.49
     பெரும்பாலும்
    0.48
    两侧
    0.48
    博物馆
    0.46
    作用
    0.45
    旕
    0.45
    峙
    0.44
    ﻀ
    0.44
    ╫
    0.44
    雩
    0.44
    POSITIVE LOGITS
     real
    0.52
     messengers
    0.50
    pa
    0.48
    frames
    0.48
    AB
    0.48
    on
    0.47
    2
    0.47
     anaerobic
    0.46
    real
    0.45
    cb
    0.45
    Activations Density 0.000%

    No Known Activations