© 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. 3680
    Prev
    Next
    INDEX
    Explanations

    technical terms, symbols, and non-English words

    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
    ़
    1.50
    ва
    1.38
     Même
    1.36
    𝗘
    1.35
     Oed
    1.33
    𝗲
    1.31
     இது
    1.30
    НИ
    1.29
    ность
    1.28
    𝒊
    1.27
    POSITIVE LOGITS
     vistos
    1.28
    ません
    1.28
    aneous
    1.26
     zich
    1.25
     extenso
    1.25
    รียม
    1.24
    လီ
    1.22
    ファスナー
    1.21
     haft
    1.20
     hefyd
    1.20
    Activations Density 0.000%

    No Known Activations