© 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
    2. Gemma-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9223
    Prev
    Next
    INDEX
    Explanations

    show

    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
    nému
    0.69
    ientôt
    0.66
     уту
    0.66
     vérit
    0.63
    碖
    0.63
    คม
    0.62
    吐槽
    0.61
    నే
    0.61
    IMPLEMENT
    0.60
    നെ
    0.60
    POSITIVE LOGITS
     show
    4.25
     shows
    4.06
     showing
    4.03
    show
    3.81
     showed
    3.68
     Show
    3.66
     Shows
    3.60
    Show
    3.55
    showing
    3.52
    shows
    3.49
    Activations Density 0.498%

    No Known Activations