© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9310
    Prev
    Next
    INDEX
    Explanations

    different

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    शियन
    0.65
    දය
    0.65
     Variables
    0.64
    BarStyle
    0.64
     Arturo
    0.63
    慣
    0.63
    ारक
    0.62
    종
    0.62
     переменных
    0.62
    变量
    0.62
    POSITIVE LOGITS
     khác
    0.84
    Different
    0.76
     different
    0.75
     diferente
    0.74
     सांस
    0.74
    different
    0.73
     diferentes
    0.73
     διαφορε
    0.72
     Contr
    0.72
     berbeda
    0.71
    Activations Density 0.032%

    No Known Activations