© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88614
    Prev
    Next
    INDEX
    Explanations

    won't

    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_18_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
     for
    0.29
    4
    0.28
     Ще
    0.28
     https
    0.28
    https
    0.27
     czyli
    0.26
    ニ
    0.25
     Fehl
    0.24
     skole
    0.24
     Ни
    0.24
    POSITIVE LOGITS
     фаразлау
    0.27
    <unused420>
    0.27
    ')"
    0.25
     අව
    0.24
     увиде
    0.24
    бав
    0.24
    ubah
    0.23
    <unused335>
    0.23
    <unused2132>
    0.23
    withstanding
    0.23
    Activations Density 0.009%

    No Known Activations