© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33630
    Prev
    Next
    INDEX
    Explanations

    large language model

    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
    随
    0.41
    ﻂ
    0.37
    Vaterpolo
    0.37
    剎
    0.35
    隨
    0.35
    ühm
    0.35
     ያስፈል
    0.35
    ச்சல்
    0.34
    𝚝
    0.33
    احة
    0.33
    POSITIVE LOGITS
    LS
    0.46
     LD
    0.44
     LS
    0.42
    LD
    0.42
    ۴
    0.41
     LF
    0.40
     LR
    0.39
    LF
    0.39
    KS
    0.38
    LDL
    0.37
    Activations Density 0.013%

    No Known Activations