© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5341
    Prev
    Next
    INDEX
    Explanations

    intrusive thoughts

    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
    ε
    1.36
    ך
    1.35
    ть
    1.30
     isa
    1.28
    Waar
    1.24
    en
    1.20
    +}$
    1.19
    ون
    1.17
    ties
    1.16
    בש
    1.15
    POSITIVE LOGITS
     magnifying
    1.62
     lensing
    1.61
    lccc
    1.53
     yawning
    1.52
     TMD
    1.49
    cjs
    1.48
     lymphocytes
    1.47
     demolish
    1.45
    nep
    1.45
    道府県
    1.45
    Activations Density 0.018%

    No Known Activations