© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    second language

    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
    ্বস্ত
    1.26
    ্ড
    1.24
    𝗲
    1.22
     majestic
    1.13
    𝘁
    1.13
    ज्ञ
    1.11
    ્વા
    1.10
    ান
    1.09
    𝗿
    1.07
    मुंबई
    1.07
    POSITIVE LOGITS
    nd
    1.72
    ن
    1.39
    ND
    1.21
    ik
    1.20
    ৭
    1.20
     représentant
    1.19
    твы
    1.17
     arrec
    1.16
     contemplates
    1.10
     able
    1.10
    Activations Density 0.275%

    No Known Activations