© 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. 9078
    Prev
    Next
    INDEX
    Explanations

    financial quarters

    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
     Q
    3.24
    Q
    3.09
     Quarter
    3.08
     quarter
    3.07
    Quarter
    2.78
     quarters
    2.69
     q
    2.52
    quarter
    2.51
    q
    2.37
    Ｑ
    2.24
    POSITIVE LOGITS
     কিছুদিন
    0.65
     صبح
    0.64
    ोम
    0.63
     araw
    0.62
    owels
    0.60
    اريخ
    0.60
    हतक
    0.59
     शिवलिंग
    0.58
    ्लाई
    0.58
    ixel
    0.58
    Activations Density 0.046%

    No Known Activations