© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    django.conf imports

    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
    ు
    2.96
    ди
    2.45
    ع
    2.35
    ره
    2.34
     Съ
    2.33
    ின்
    2.32
    дно
    2.19
     gebra
    2.14
    ский
    2.13
    ை
    2.12
    POSITIVE LOGITS
     singularities
    2.54
    स्परिक
    2.40
     biographies
    2.35
     lubrication
    2.30
    UserInfo
    2.30
     bioavailability
    2.29
    াকিস্ত
    2.26
    𝚕
    2.25
    AccessToken
    2.23
     parametrization
    2.22
    Activations Density 0.000%

    No Known Activations