Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3917
    Prev
    Next
    INDEX
    Explanations

    increase the

    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
    ১
    1.25
     kuten
    1.23
    zelf
    1.23
    ﻊ
    1.22
     transcends
    1.22
     sorts
    1.12
    প্রায়
    1.08
    遢
    1.07
    Α
    1.06
    აწ
    1.05
    POSITIVE LOGITS
     সংখ্যক
    1.33
     çıkan
    1.28
     इससे
    1.21
    স
    1.19
    lighter
    1.19
     इंतजार
    1.19
    LOADSTRING
    1.18
     участие
    1.16
     lumi
    1.15
    werden
    1.15
    Activations Density 0.013%

    No Known Activations