© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3320
    Prev
    Next
    INDEX
    Explanations

    flexible work arrangements

    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_5_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
    ٹ
    1.19
     steht
    1.17
     tris
    1.16
     empate
    1.14
    ની
    1.13
    もの
    1.08
    ের
    1.08
     ocorr
    1.08
    皙
    1.07
     doel
    1.06
    POSITIVE LOGITS
    ﻲ
    1.45
    夠
    1.29
     notorious
    1.19
    ️
    1.17
     inaugural
    1.16
    odore
    1.16
    nt
    1.16
    theless
    1.15
    asmuch
    1.15
     gotta
    1.13
    Activations Density 0.000%

    No Known Activations