© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92077
    Prev
    Next
    INDEX
    Explanations

    fall / fallen

    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_11_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
     THE
    0.60
     Ν
    0.57
     THERE
    0.56
    𝐾
    0.55
     MODELS
    0.55
    ﻻ
    0.54
    bran
    0.54
     THEM
    0.53
    ING
    0.52
     CONTROL
    0.52
    POSITIVE LOGITS
    지
    0.75
     majú
    0.73
    ocsát
    0.65
    يل
    0.63
    يكية
    0.63
    يت
    0.62
    يق
    0.60
    的
    0.59
    （
    0.59
    يد
    0.59
    Activations Density 0.001%

    No Known Activations