© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4987
    Prev
    Next
    INDEX
    Explanations

    tension and related suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    шая
    2.62
     superscript
    2.56
    speople
    2.53
    tagName
    2.53
    al
    2.53
    ﻱ
    2.47
     ettha
    2.43
    dest
    2.41
    ce
    2.40
    鎸
    2.38
    POSITIVE LOGITS
    લ
    2.73
    த
    2.47
    इस
    2.45
     тока
    2.43
     конечно
    2.37
     года
    2.36
     demeanor
    2.28
     انواع
    2.23
     odc
    2.19
     mesmos
    2.18
    Activations Density 0.055%

    No Known Activations