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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3608
    Prev
    Next
    INDEX
    Explanations

    organization types

    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
     atriz
    2.52
     tiempos
    2.34
     testament
    2.27
    ك
    2.22
     olas
    2.18
    垒
    2.17
    お
    2.17
    u
    2.17
     caract
    2.11
     precedente
    2.10
    POSITIVE LOGITS
    Translatef
    2.64
    LaunchScheme
    2.48
    Arial
    2.33
    ి
    2.30
    ⏤
    2.28
    此之外
    2.28
     MEP
    2.19
     গান্ধীর
    2.19
    evident
    2.18
     bustle
    2.17
    Activations Density 0.443%

    No Known Activations