© 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. 5245
    Prev
    Next
    INDEX
    Explanations

    science Nasional

    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
    𝐬
    3.43
    𝐲
    3.30
    𝐥
    3.17
     hysteresis
    3.16
    𝐩
    3.08
    𝐘
    3.00
    𝐈
    2.97
    𝐠
    2.83
    𝐦
    2.83
    weixin
    2.82
    POSITIVE LOGITS
    т
    3.24
    क
    2.63
    ли
    2.62
    ந்த
    2.54
    ко
    2.52
     rebuttal
    2.48
     ficción
    2.44
    ку
    2.41
     Правда
    2.35
    тта
    2.29
    Activations Density 0.044%

    No Known Activations