© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6584
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
     обеспечи
    2.44
    いただけ
    2.18
    是用
    2.16
    her
    2.16
    是
    2.15
    দের
    2.15
    ලේ
    2.11
    ড
    2.09
    தான்
    2.09
     došlo
    2.08
    POSITIVE LOGITS
    shore
    2.52
    𝑝
    2.17
    groupBox
    2.07
    ि
    2.06
    𝑙
    2.04
    ="/"
    2.03
    spoken
    2.03
    sortBy
    2.03
    Aber
    2.00
    ˬ
    1.99
    Activations Density 0.031%

    No Known Activations