© 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. 5326
    Prev
    Next
    INDEX
    Explanations

    by far

    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
    en
    2.73
    ာ
    2.43
    ार
    2.20
    o
    2.18
     deber
    2.16
    ر
    2.12
    ar
    2.10
     Bunu
    2.06
    !\!\
    2.05
    ু
    2.02
    POSITIVE LOGITS
    NSLog
    2.39
    нің
    2.27
     weaving
    2.15
    hemian
    2.15
    chman
    2.10
    ил
    2.09
    nä
    2.08
     infall
    2.06
    ₤
    2.06
     meandering
    2.06
    Activations Density 0.008%

    No Known Activations