© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165029
    Prev
    Next
    INDEX
    Explanations

    kotlin class declaration

    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
    ddots
    0.38
    порта
    0.38
    atanga
    0.37
    ızı
    0.36
    ванта
    0.35
     محاس
    0.35
    𝙊
    0.35
    торая
    0.35
    ൊരു
    0.34
    эта
    0.34
    POSITIVE LOGITS
     lyd
    0.38
     darum
    0.36
     imp
    0.36
     vermeiden
    0.35
    妑
    0.34
     veniam
    0.33
     um
    0.33
     Um
    0.33
     moderation
    0.33
     Iy
    0.33
    Activations Density 0.000%

    No Known Activations