© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130603
    Prev
    Next
    INDEX
    Explanations

    numerical sequences after slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    铄
    0.44
    ようになる
    0.38
     safest
    0.36
    NP
    0.35
    下
    0.35
     safer
    0.34
    なくなる
    0.34
    总结
    0.34
    装
    0.34
    NJ
    0.34
    POSITIVE LOGITS
    ভিড
    0.44
     बदनाम
    0.43
    odis
    0.42
     certaines
    0.40
     algunas
    0.40
    ction
    0.39
     několik
    0.39
     mempert
    0.38
    Probability
    0.38
     Khat
    0.38
    Activations Density 0.001%

    No Known Activations