© 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. 3354
    Prev
    Next
    INDEX
    Explanations

    habitat loss, preferences, or restoration

    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
    𝐤
    0.72
    𝐭
    0.65
    Результа
    0.64
    enzen
    0.64
     поверну
    0.61
     तर
    0.60
    ры
    0.60
    靂
    0.58
     želite
    0.58
    ὺ
    0.57
    POSITIVE LOGITS
     участ
    0.72
    家
    0.70
     abode
    0.69
     Directory
    0.67
     embankment
    0.66
     asymptote
    0.66
     Epidemiology
    0.65
     excavator
    0.64
     Ginkuhà
    0.64
     растя
    0.64
    Activations Density 0.008%

    No Known Activations