© 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. 3473
    Prev
    Next
    INDEX
    Explanations

    partial class

    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
    ل
    2.05
    as
    1.87
    на
    1.68
    HEIM
    1.53
    љи
    1.51
    ༅
    1.48
    لل
    1.47
    ্স
    1.47
    VING
    1.46
     overwhelming
    1.45
    POSITIVE LOGITS
     incrementar
    1.76
     servir
    1.74
     tecnica
    1.73
     twee
    1.69
     secretos
    1.67
     miserably
    1.66
     novo
    1.66
     referentes
    1.66
     pilas
    1.66
     secreto
    1.65
    Activations Density 0.000%

    No Known Activations