© 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. 3148
    Prev
    Next
    INDEX
    Explanations

    just because ... doesn't mean

    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
    д
    0.49
    Là
    0.44
     Technische
    0.41
    Кар
    0.41
     вле
    0.40
    d
    0.40
    tabla
    0.40
    lovers
    0.39
    contenedor
    0.39
    tolerance
    0.38
    POSITIVE LOGITS
    VSLU
    0.67
    मताओं
    0.59
     ويكيميديا
    0.59
    ülete
    0.58
    ROTTLE
    0.57
     chanted
    0.57
    nextSend
    0.56
    ع
    0.56
    lsulfanyl
    0.55
    uvi
    0.54
    Activations Density 0.004%

    No Known Activations