© 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. 5644
    Prev
    Next
    INDEX
    Explanations

    automated

    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
    or
    2.71
    াল
    2.38
    ்
    2.38
    ers
    2.33
    amounts
    2.24
    𝑵
    2.21
    رځ
    2.18
    وڑا
    2.17
    rocyte
    2.12
     amounts
    2.04
    POSITIVE LOGITS
    मोबाइल
    3.09
    থাৎ
    2.65
    जम्मू
    2.42
    ر
    2.40
    ক্রিয়
    2.36
    ちなみに
    2.36
    स्फ
    2.33
    ت
    2.30
    fledged
    2.29
    ிறது
    2.22
    Activations Density 0.088%

    No Known Activations