© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    ground-based

    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
    т
    2.42
    ᶤ
    2.39
    খানি
    2.39
    ς
    2.28
    {~
    2.25
    عدد
    2.24
    athy
    2.20
     quedando
    2.19
    राधिक
    2.16
     avanz
    2.10
    POSITIVE LOGITS
    𝐄
    3.01
    names
    2.69
     zmi
    2.62
    щихся
    2.58
     homozygous
    2.56
    scrollTo
    2.56
    दार
    2.55
    ૃહ
    2.54
    റെ
    2.53
     chromospheric
    2.52
    Activations Density 0.012%

    No Known Activations