© 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. 6210
    Prev
    Next
    INDEX
    Explanations

    German suffixes like keit

    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
    াতে
    0.68
     solucionar
    0.67
    ون
    0.65
    ן
    0.64
     utens
    0.64
     cabelos
    0.63
     flexDirection
    0.62
    ീ
    0.59
     Обра
    0.59
     Guarda
    0.59
    POSITIVE LOGITS
    일상
    0.55
     xét
    0.52
    his
    0.51
    has
    0.49
    placeholder
    0.49
    hh
    0.49
    toluene
    0.48
    says
    0.48
    single
    0.48
    $[\
    0.48
    Activations Density 0.006%

    No Known Activations